init leaderboard

Makefile

@@ -1,13 +0,0 @@
-.PHONY: style format
-
-
-style:
-	python -m black --line-length 119 .
-	python -m isort .
-	ruff check --fix .
-
-
-quality:
-	python -m black --check --line-length 119 .
-	python -m isort --check-only .
-	ruff check .

README.md

@@ -1,46 +1,22 @@
 ---
-title: GenerativeReasoningBenchmark
-emoji: 🥇
-colorFrom: green
-colorTo: indigo
+title: Reward Bench Leaderboard
+emoji: 📐
+colorFrom: pink
+colorTo: blue
 sdk: gradio
+sdk_version: 4.36.0
 app_file: app.py
 pinned: true
 license: apache-2.0
-short_description: Duplicate this leaderboard to initialize your own!
-sdk_version: 5.19.0
+tags:
+- leaderboard
 ---
 
-# Start the configuration
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
-Most of the variables to change for a default leaderboard are in `src/env.py` (replace the path for your leaderboard) and `src/about.py` (for tasks).
-
-Results files should have the following format and be stored as json files:
-```json
-{
-    "config": {
-        "model_dtype": "torch.float16", # or torch.bfloat16 or 8bit or 4bit
-        "model_name": "path of the model on the hub: org/model",
-        "model_sha": "revision on the hub",
-    },
-    "results": {
-        "task_name": {
-            "metric_name": score,
-        },
-        "task_name2": {
-            "metric_name": score,
-        }
-    }
-}
+To develop this app, it can be run with:
+```
+gradio app.py
 ```
 
-Request files are created automatically by this tool.
-
-If you encounter problem on the space, don't hesitate to restart it to remove the create eval-queue, eval-queue-bk, eval-results and eval-results-bk created folder.
-
-# Code logic for more complex edits
-
-You'll find 
-- the main table' columns names and properties in `src/display/utils.py`
-- the logic to read all results and request files, then convert them in dataframe lines, in `src/leaderboard/read_evals.py`, and `src/populate.py`
-- the logic to allow or filter submissions in `src/submission/submit.py` and `src/submission/check_validity.py`
+Paper: https://arxiv.org/abs/2403.13787

app.py

@@ -1,204 +1,146 @@
+import json
+from pathlib import Path
+
 import gradio as gr
-from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns
 import pandas as pd
-from apscheduler.schedulers.background import BackgroundScheduler
-from huggingface_hub import snapshot_download
-
-from src.about import (
-    CITATION_BUTTON_LABEL,
-    CITATION_BUTTON_TEXT,
-    EVALUATION_QUEUE_TEXT,
-    INTRODUCTION_TEXT,
-    LLM_BENCHMARKS_TEXT,
-    TITLE,
-)
-from src.display.css_html_js import custom_css
-from src.display.utils import (
-    BENCHMARK_COLS,
-    COLS,
-    EVAL_COLS,
-    EVAL_TYPES,
-    AutoEvalColumn,
-    ModelType,
-    fields,
-    WeightType,
-    Precision
-)
-from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, QUEUE_REPO, REPO_ID, RESULTS_REPO, TOKEN
-from src.populate import get_evaluation_queue_df, get_leaderboard_df
-from src.submission.submit import add_new_eval
-
-
-def restart_space():
-    API.restart_space(repo_id=REPO_ID)
-
-### Space initialisation
-try:
-    print(EVAL_REQUESTS_PATH)
-    snapshot_download(
-        repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
-    )
-except Exception:
-    restart_space()
-try:
-    print(EVAL_RESULTS_PATH)
-    snapshot_download(
-        repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
-    )
-except Exception:
-    restart_space()
-
-
-LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS)
-
-(
-    finished_eval_queue_df,
-    running_eval_queue_df,
-    pending_eval_queue_df,
-) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
-
-def init_leaderboard(dataframe):
-    if dataframe is None or dataframe.empty:
-        raise ValueError("Leaderboard DataFrame is empty or None.")
-    return Leaderboard(
-        value=dataframe,
-        datatype=[c.type for c in fields(AutoEvalColumn)],
-        select_columns=SelectColumns(
-            default_selection=[c.name for c in fields(AutoEvalColumn) if c.displayed_by_default],
-            cant_deselect=[c.name for c in fields(AutoEvalColumn) if c.never_hidden],
-            label="Select Columns to Display:",
-        ),
-        search_columns=[AutoEvalColumn.model.name, AutoEvalColumn.license.name],
-        hide_columns=[c.name for c in fields(AutoEvalColumn) if c.hidden],
-        filter_columns=[
-            ColumnFilter(AutoEvalColumn.model_type.name, type="checkboxgroup", label="Model types"),
-            ColumnFilter(AutoEvalColumn.precision.name, type="checkboxgroup", label="Precision"),
-            ColumnFilter(
-                AutoEvalColumn.params.name,
-                type="slider",
-                min=0.01,
-                max=150,
-                label="Select the number of parameters (B)",
-            ),
-            ColumnFilter(
-                AutoEvalColumn.still_on_hub.name, type="boolean", label="Deleted/incomplete", default=True
-            ),
-        ],
-        bool_checkboxgroup_label="Hide models",
-        interactive=False,
-    )
+
+from texts import TITLE, DESCRIPTION
+from process_data import load_average_data, load_hard_data, load_easy_data
+from display import custom_css
+BENCHMARKS_TO_SKIP = []
+
+color_map = {
+    "Pretrained": "#7497db",
+    "RL": "#E8ECF2",
+    "Finetuned": "#ffcd75",
+    # "DPO": "#75809c",
+}
+
+model_name_map = {
+    "qwen2.5-3b-instruct": "Qwen/Qwen2.5-3B-Instruct",
+    "qwen2.5-7b-instruct": "Qwen/Qwen2.5-7B-Instruct",
+    "qwen2.5-14b-instruct": "Qwen/Qwen2.5-14B-Instruct",
+    "qwen2.5-32b-instruct": "Qwen/Qwen2.5-32B-Instruct",
+    "qwen2.5-72b-instruct": "Qwen/Qwen2.5-72B-Instruct",
+    "llama-3.1-8b-instruct": "Meta-Llama/Llama-3.1-8B-Instruct",
+    "llama-3.1-70b-instruct": "Meta-Llama/Llama-3.1-70B-Instruct",
+    "llama-3.2-3b-instruct": "Meta-Llama/Llama-3.2-3B-Instruct",
+    "llama-3.3-70b-instruct": "Meta-Llama/Llama-3.3-70B-Instruct",
+    "mistral-large-instruct-2411": "Mistral/Mistral-Large-2411",
+    "gemma-2-27b-it": "google/gemma-2-27b-it",
+    "gemma-2-9b-it": "google/gemma-2-9b-it",
+    "deepseek-v3": "deepseek-ai/DeepSeek-V3",
+    "deepseek-r1": "deepseek-ai/DeepSeek-R1",
+    "qwq-32b": "Qwen/QwQ-32B",
+    "yi-lightning": "Yi/Yi-Lightning",
+    'gpt-3.5-turbo': "openai/gpt-3.5-turbo",
+    'gpt-4o': "openai/gpt-4o",
+    'gpt-4o-mini': "openai/gpt-4o-mini",
+    'o1-mini': "openai/o1-mini",
+    'claude-3.5-haiku': "anthropic/claude-3.5-haiku",
+    'claude-3.5-sonnet': "anthropic/claude-3.5-sonnet",
+}
+
+def map_model_name(model_id):
+    if model_id not in model_name_map.keys():
+        return model_id
+    else:
+        return model_name_map[model_id]
+
+# 定义函数，将模型名称转换为带有链接的 HTML 格式
+def model_hyperlink(link, model_name):
+    return f'<a target="_blank" href="{link}" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">{model_name}</a>'
+
+def make_clickable_model(model_name):
+    link = f"https://huggingface.co/{model_name}"
+    return model_hyperlink(link, model_name)
+
+rl_models = ['deepseek-r1', 'o1-mini']
+def map_model_type(model_name):
+    if model_name in rl_models:
+        return "RL"
+    else:
+        return "Pretrained"
+    
+
+def prep_leaderboard_df():
+    average_df = load_average_data()
+    hard_df = load_hard_data()
+    easy_df = load_easy_data()
+    df = pd.concat([easy_df, hard_df, average_df], axis=1)
+    # insert a column named "Model" at the first position
+    df.insert(0, "Model", [map_model_name(idx) for idx in df.index])
+    df.insert(1, "Model Type", [map_model_type(idx) for idx in df.index])
+    # 对 Model 列应用函数，将模型名称转换为链接形式
+    # df['Model'] = df['Model'].apply(make_clickable_model)
+    df = df.round(2)
+    return df
+
+leaderboard_df = prep_leaderboard_df()
+
+
+# Function to update the table based on search query
+def filter_and_search(cols: list[str], search_query: str, agg: str):
+    print("filter")
+    df = leaderboard_df
+    search_terms = "Model"
+    if len(search_query) > 0:
+        search_terms = search_query.split(";")
+        search_terms = [term.strip().lower() for term in search_terms]
+        pattern = "|".join(search_terms)
+        df = df[df["Model"].str.lower().str.contains(pattern, regex=True)]
+        # Drop any columns which are all NaN
+        df = df.dropna(how="all", axis=1)
+
+    if len(cols) > 0:
+        index_cols = list(leaderboard_df.columns[:1])
+        new_cols = index_cols + cols
+        df = df.copy()[new_cols]
+        df = df.copy().dropna(how="all", axis=0, subset=[c for c in df.columns if c in cols])
+
+        df[cols] = df[cols].apply(pd.to_numeric, errors='coerce')
+        df = df.sort_values(by=cols, ascending=False, na_position='last')
+        df[cols] = df[cols].astype(str)
+    return df
 
 
 demo = gr.Blocks(css=custom_css)
+
 with demo:
     gr.HTML(TITLE)
-    gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
-
-    with gr.Tabs(elem_classes="tab-buttons") as tabs:
-        with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
-            leaderboard = init_leaderboard(LEADERBOARD_DF)
-
-        with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
-            gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
-
-        with gr.TabItem("🚀 Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
-            with gr.Column():
-                with gr.Row():
-                    gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
-
-                with gr.Column():
-                    with gr.Accordion(
-                        f"✅ Finished Evaluations ({len(finished_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            finished_eval_table = gr.components.Dataframe(
-                                value=finished_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
-                    with gr.Accordion(
-                        f"🔄 Running Evaluation Queue ({len(running_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            running_eval_table = gr.components.Dataframe(
-                                value=running_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
-
-                    with gr.Accordion(
-                        f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            pending_eval_table = gr.components.Dataframe(
-                                value=pending_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
-            with gr.Row():
-                gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")
-
-            with gr.Row():
-                with gr.Column():
-                    model_name_textbox = gr.Textbox(label="Model name")
-                    revision_name_textbox = gr.Textbox(label="Revision commit", placeholder="main")
-                    model_type = gr.Dropdown(
-                        choices=[t.to_str(" : ") for t in ModelType if t != ModelType.Unknown],
-                        label="Model type",
-                        multiselect=False,
-                        value=None,
-                        interactive=True,
-                    )
-
-                with gr.Column():
-                    precision = gr.Dropdown(
-                        choices=[i.value.name for i in Precision if i != Precision.Unknown],
-                        label="Precision",
-                        multiselect=False,
-                        value="float16",
-                        interactive=True,
-                    )
-                    weight_type = gr.Dropdown(
-                        choices=[i.value.name for i in WeightType],
-                        label="Weights type",
-                        multiselect=False,
-                        value="Original",
-                        interactive=True,
-                    )
-                    base_model_name_textbox = gr.Textbox(label="Base model (for delta or adapter weights)")
-
-            submit_button = gr.Button("Submit Eval")
-            submission_result = gr.Markdown()
-            submit_button.click(
-                add_new_eval,
-                [
-                    model_name_textbox,
-                    base_model_name_textbox,
-                    revision_name_textbox,
-                    precision,
-                    weight_type,
-                    model_type,
-                ],
-                submission_result,
+    with gr.Column():
+        gr.Markdown(DESCRIPTION, elem_classes="markdown-text")
+        with gr.Row():
+            search_bar = gr.Textbox(placeholder="Search for your model...", show_label=False)
+
+            cols_bar = gr.CheckboxGroup(
+                choices=[c for c in leaderboard_df.columns[1:] if c != "Average"],
+                show_label=False,
+                # info="Select columns to display",
             )
+        with gr.Group():
+            leaderboard_table = gr.Dataframe(
+                value=leaderboard_df,
+                wrap=True,
+                # column_widths=[400, 110] + [(260 + len(c)) for c in leaderboard_df.columns[1:]],
+            )
+
+    cols_bar.change(filter_and_search, inputs=[cols_bar, search_bar], outputs=[leaderboard_table])
+    search_bar.submit(filter_and_search, inputs=[cols_bar, search_bar], outputs=[leaderboard_table])
 
     with gr.Row():
-        with gr.Accordion("📙 Citation", open=False):
+        with gr.Accordion("📚 Citation", open=False):
             citation_button = gr.Textbox(
-                value=CITATION_BUTTON_TEXT,
-                label=CITATION_BUTTON_LABEL,
-                lines=20,
+                value=r"""@article{lin2025generative,
+  title={Generative Evaluation of Complex Reasoning in Large Language Models},
+  author={Lin, Haowei and Wang, Xiangyu and Yan, Ruilin and Huang, Baizhou and Ye, Haotian and Zhu, Jianhua and Wang, Zihao and Zou, James and Ma, Jianzhu and Liang, Yitao},
+  journal={arXiv preprint arXiv:2504.02810},
+  year={2025}
+}""",
+                lines=7,
+                label="Copy the following to cite these results.",
                 elem_id="citation-button",
                 show_copy_button=True,
             )
 
-scheduler = BackgroundScheduler()
-scheduler.add_job(restart_space, "interval", seconds=1800)
-scheduler.start()
-demo.queue(default_concurrency_limit=40).launch()
+demo.launch()

data/action_count_0402.json

@@ -0,0 +1,1819 @@
+{
+    "RelicEnv": {
+        "qwen2.5-3b-instruct": 0.576,
+        "qwen2.5-7b-instruct": 0.5228666666666666,
+        "qwen2.5-14b-instruct": 0.3816,
+        "qwen2.5-32b-instruct": 0.4269333333333333,
+        "qwen2.5-72b-instruct": 0.3848666666666667,
+        "llama-3.1-8b-instruct": 0.6459999999999999,
+        "llama-3.1-70b-instruct": 0.41696190476190476,
+        "llama-3.2-3b-instruct": 0.5766095238095238,
+        "llama-3.3-70b-instruct": 0.33466666666666656,
+        "mistral-large-instruct-2411": 0.492,
+        "gemma-2-27b-it": 0.48513333333333336,
+        "gemma-2-9b-it": 0.668695238095238,
+        "deepseek-v3": 0.5289999999999999,
+        "deepseek-r1": 0.523295238095238,
+        "qwq-32b": 0.5080190476190476,
+        "Average": 0.49817650793650786
+    },
+    "HerbEnv": {
+        "qwen2.5-3b-instruct": 0.6345333333333334,
+        "qwen2.5-7b-instruct": 0.6564,
+        "qwen2.5-14b-instruct": 0.4304,
+        "qwen2.5-32b-instruct": 0.4564666666666667,
+        "qwen2.5-72b-instruct": 0.43260000000000004,
+        "llama-3.1-8b-instruct": 0.7072,
+        "llama-3.1-70b-instruct": 0.4986,
+        "llama-3.2-3b-instruct": 0.7223333333333333,
+        "llama-3.3-70b-instruct": 0.49833333333333335,
+        "mistral-large-instruct-2411": 0.5494,
+        "gemma-2-27b-it": 0.5511999999999999,
+        "gemma-2-9b-it": 0.7503333333333334,
+        "deepseek-v3": 0.42873333333333336,
+        "deepseek-r1": 0.5064666666666666,
+        "qwq-32b": 0.5062666666666666,
+        "Average": 0.5552844444444445
+    },
+    "TransdimensionalEnv": {
+        "qwen2.5-3b-instruct": 0.8419333333333332,
+        "qwen2.5-7b-instruct": 0.7645333333333333,
+        "qwen2.5-14b-instruct": 0.5994666666666667,
+        "qwen2.5-32b-instruct": 0.5703333333333334,
+        "qwen2.5-72b-instruct": 0.5725333333333333,
+        "llama-3.1-8b-instruct": 0.8210666666666666,
+        "llama-3.1-70b-instruct": 0.5205333333333333,
+        "llama-3.2-3b-instruct": 0.7700666666666665,
+        "llama-3.3-70b-instruct": 0.5580666666666667,
+        "mistral-large-instruct-2411": 0.6012666666666666,
+        "gemma-2-27b-it": 0.7089999999999999,
+        "gemma-2-9b-it": 0.9037333333333333,
+        "deepseek-v3": 0.6178,
+        "deepseek-r1": 0.5913999999999999,
+        "qwq-32b": 0.653,
+        "Average": 0.6729822222222223
+    },
+    "SorcererEnv": {
+        "qwen2.5-3b-instruct": 1.0192666666666665,
+        "qwen2.5-7b-instruct": 1.0209333333333332,
+        "qwen2.5-14b-instruct": 0.7593333333333334,
+        "qwen2.5-32b-instruct": 0.8110666666666667,
+        "qwen2.5-72b-instruct": 0.7878666666666667,
+        "llama-3.1-8b-instruct": 1.0720666666666667,
+        "llama-3.1-70b-instruct": 0.7602666666666668,
+        "llama-3.2-3b-instruct": 1.0208666666666666,
+        "llama-3.3-70b-instruct": 0.7425333333333334,
+        "mistral-large-instruct-2411": 0.8440666666666667,
+        "gemma-2-27b-it": 0.8615333333333333,
+        "gemma-2-9b-it": 1.1598666666666666,
+        "deepseek-v3": 0.8091333333333333,
+        "deepseek-r1": 0.8958,
+        "qwq-32b": 0.8321999999999999,
+        "Average": 0.89312
+    },
+    "QuantumEnv": {
+        "qwen2.5-3b-instruct": 1.0699999999999998,
+        "qwen2.5-7b-instruct": 0.8955333333333334,
+        "qwen2.5-14b-instruct": 0.7378666666666667,
+        "qwen2.5-32b-instruct": 0.7390666666666666,
+        "qwen2.5-72b-instruct": 0.649,
+        "llama-3.1-8b-instruct": 1.083,
+        "llama-3.1-70b-instruct": 0.7020666666666668,
+        "llama-3.2-3b-instruct": 1.0911333333333335,
+        "llama-3.3-70b-instruct": 0.6975333333333333,
+        "mistral-large-instruct-2411": 0.7345333333333333,
+        "gemma-2-27b-it": 0.7445333333333334,
+        "gemma-2-9b-it": 1.1341999999999999,
+        "deepseek-v3": 0.7477333333333334,
+        "deepseek-r1": 0.7415333333333334,
+        "qwq-32b": 0.7549333333333333,
+        "Average": 0.8348444444444444
+    },
+    "AstronomyEnv": {
+        "qwen2.5-3b-instruct": 0.8259333333333334,
+        "qwen2.5-7b-instruct": 0.8053333333333335,
+        "qwen2.5-14b-instruct": 0.4937333333333333,
+        "qwen2.5-32b-instruct": 0.5776666666666666,
+        "qwen2.5-72b-instruct": 0.4677999999999999,
+        "llama-3.1-8b-instruct": 0.836,
+        "llama-3.1-70b-instruct": 0.5228,
+        "llama-3.2-3b-instruct": 0.8694000000000001,
+        "llama-3.3-70b-instruct": 0.5525333333333332,
+        "mistral-large-instruct-2411": 0.4943999999999999,
+        "gemma-2-27b-it": 0.6376000000000001,
+        "gemma-2-9b-it": 0.7730666666666668,
+        "deepseek-v3": 0.5540666666666666,
+        "deepseek-r1": 0.4287333333333333,
+        "qwq-32b": 0.4580666666666667,
+        "Average": 0.6198088888888889
+    },
+    "MusicGenresEnv": {
+        "qwen2.5-3b-instruct": 0.6298666666666667,
+        "qwen2.5-7b-instruct": 0.5864666666666667,
+        "qwen2.5-14b-instruct": 0.3452,
+        "qwen2.5-32b-instruct": 0.37546666666666667,
+        "qwen2.5-72b-instruct": 0.398,
+        "llama-3.1-8b-instruct": 0.6799999999999999,
+        "llama-3.1-70b-instruct": 0.44333333333333336,
+        "llama-3.2-3b-instruct": 0.8452,
+        "llama-3.3-70b-instruct": 0.49539999999999995,
+        "mistral-large-instruct-2411": 0.3673333333333333,
+        "gemma-2-27b-it": 0.5542666666666667,
+        "gemma-2-9b-it": 0.6927333333333332,
+        "deepseek-v3": 0.3997333333333334,
+        "deepseek-r1": 0.3074,
+        "qwq-32b": 0.30833333333333335,
+        "Average": 0.49524888888888896
+    },
+    "CloudEnv": {
+        "qwen2.5-3b-instruct": 0.7101999999999999,
+        "qwen2.5-7b-instruct": 0.6398380952380952,
+        "qwen2.5-14b-instruct": 0.2948095238095238,
+        "qwen2.5-32b-instruct": 0.39837142857142854,
+        "qwen2.5-72b-instruct": 0.3368666666666667,
+        "llama-3.1-8b-instruct": 0.6846857142857142,
+        "llama-3.1-70b-instruct": 0.4453333333333333,
+        "llama-3.2-3b-instruct": 0.7733333333333332,
+        "llama-3.3-70b-instruct": 0.4490380952380952,
+        "mistral-large-instruct-2411": 0.23912380952380952,
+        "gemma-2-27b-it": 0.406047619047619,
+        "gemma-2-9b-it": 0.675342857142857,
+        "deepseek-v3": 0.3188952380952381,
+        "deepseek-r1": 0.16405714285714285,
+        "qwq-32b": 0.20542857142857143,
+        "Average": 0.44942476190476194
+    },
+    "CuisineEnv": {
+        "qwen2.5-3b-instruct": 1.0595999999999999,
+        "qwen2.5-7b-instruct": 1.085838095238095,
+        "qwen2.5-14b-instruct": 0.882352380952381,
+        "qwen2.5-32b-instruct": 0.9331333333333334,
+        "qwen2.5-72b-instruct": 0.873,
+        "llama-3.1-8b-instruct": 1.1925238095238095,
+        "llama-3.1-70b-instruct": 0.9360190476190476,
+        "llama-3.2-3b-instruct": 1.2040571428571427,
+        "llama-3.3-70b-instruct": 1.0072571428571429,
+        "mistral-large-instruct-2411": 0.9003428571428571,
+        "gemma-2-27b-it": 1.1492285714285715,
+        "gemma-2-9b-it": 1.2268285714285714,
+        "deepseek-v3": 0.8427809523809524,
+        "deepseek-r1": 0.8026761904761905,
+        "qwq-32b": 0.8055523809523809,
+        "Average": 0.9934126984126983
+    },
+    "PlantEnv": {
+        "qwen2.5-3b-instruct": 0.6316666666666666,
+        "qwen2.5-7b-instruct": 0.6612000000000001,
+        "qwen2.5-14b-instruct": 0.6797333333333333,
+        "qwen2.5-32b-instruct": 0.7276666666666667,
+        "qwen2.5-72b-instruct": 0.6846666666666665,
+        "llama-3.1-8b-instruct": 0.7318666666666667,
+        "llama-3.1-70b-instruct": 0.6868666666666666,
+        "llama-3.2-3b-instruct": 0.7314,
+        "llama-3.3-70b-instruct": 0.739,
+        "mistral-large-instruct-2411": 0.6728666666666665,
+        "gemma-2-27b-it": 0.7182666666666666,
+        "gemma-2-9b-it": 0.7471333333333334,
+        "deepseek-v3": 0.6415333333333332,
+        "deepseek-r1": 0.6114666666666666,
+        "qwq-32b": 0.6385333333333333,
+        "Average": 0.6869244444444446
+    },
+    "HistoricalEnv": {
+        "qwen2.5-3b-instruct": 0.5945333333333332,
+        "qwen2.5-7b-instruct": 0.5029999999999999,
+        "qwen2.5-14b-instruct": 0.41719999999999996,
+        "qwen2.5-32b-instruct": 0.49926666666666664,
+        "qwen2.5-72b-instruct": 0.4616666666666667,
+        "llama-3.1-8b-instruct": 0.6741999999999999,
+        "llama-3.1-70b-instruct": 0.43866666666666665,
+        "llama-3.2-3b-instruct": 0.6622666666666666,
+        "llama-3.3-70b-instruct": 0.44580000000000003,
+        "mistral-large-instruct-2411": 0.30566666666666664,
+        "gemma-2-27b-it": 0.43679999999999997,
+        "gemma-2-9b-it": 0.6955333333333333,
+        "deepseek-v3": 0.3064,
+        "deepseek-r1": 0.1416,
+        "qwq-32b": 0.19106666666666666,
+        "Average": 0.4515777777777778
+    },
+    "GadgetEnv": {
+        "qwen2.5-3b-instruct": 0.7405999999999999,
+        "qwen2.5-7b-instruct": 0.7083999999999999,
+        "qwen2.5-14b-instruct": 0.48,
+        "qwen2.5-32b-instruct": 0.5347999999999999,
+        "qwen2.5-72b-instruct": 0.48633333333333334,
+        "llama-3.1-8b-instruct": 0.7890666666666666,
+        "llama-3.1-70b-instruct": 0.4845999999999999,
+        "llama-3.2-3b-instruct": 0.7646,
+        "llama-3.3-70b-instruct": 0.5077999999999999,
+        "mistral-large-instruct-2411": 0.6042666666666665,
+        "gemma-2-27b-it": 0.6635333333333333,
+        "gemma-2-9b-it": 0.8321333333333332,
+        "deepseek-v3": 0.5766666666666667,
+        "deepseek-r1": 0.6070666666666666,
+        "qwq-32b": 0.6155333333333333,
+        "Average": 0.6263599999999999
+    },
+    "TimeTravelEnv": {
+        "qwen2.5-3b-instruct": 0.976,
+        "qwen2.5-7b-instruct": 0.8145999999999999,
+        "qwen2.5-14b-instruct": 0.6627333333333333,
+        "qwen2.5-32b-instruct": 0.6956666666666667,
+        "qwen2.5-72b-instruct": 0.6541333333333333,
+        "llama-3.1-8b-instruct": 0.8264666666666665,
+        "llama-3.1-70b-instruct": 0.6590666666666667,
+        "llama-3.2-3b-instruct": 0.8872666666666665,
+        "llama-3.3-70b-instruct": 0.7066000000000001,
+        "mistral-large-instruct-2411": 0.7033333333333334,
+        "gemma-2-27b-it": 0.8493333333333334,
+        "gemma-2-9b-it": 1.0604666666666667,
+        "deepseek-v3": 0.7296666666666667,
+        "deepseek-r1": 0.6510666666666667,
+        "qwq-32b": 0.6808666666666667,
+        "Average": 0.7704844444444444
+    },
+    "PollutionEnv": {
+        "qwen2.5-3b-instruct": 0.8957809523809523,
+        "qwen2.5-7b-instruct": 0.8026,
+        "qwen2.5-14b-instruct": 0.6021904761904762,
+        "qwen2.5-32b-instruct": 0.6871238095238095,
+        "qwen2.5-72b-instruct": 0.6281809523809524,
+        "llama-3.1-8b-instruct": 0.9049904761904761,
+        "llama-3.1-70b-instruct": 0.609295238095238,
+        "llama-3.2-3b-instruct": 0.9090761904761905,
+        "llama-3.3-70b-instruct": 0.615352380952381,
+        "mistral-large-instruct-2411": 0.595695238095238,
+        "gemma-2-27b-it": 0.7770761904761903,
+        "gemma-2-9b-it": 0.8730190476190476,
+        "deepseek-v3": 0.6199238095238095,
+        "deepseek-r1": 0.5457142857142857,
+        "qwq-32b": 0.5781333333333333,
+        "Average": 0.7096101587301588
+    },
+    "DemographicEnv": {
+        "qwen2.5-3b-instruct": 1.2349333333333334,
+        "qwen2.5-7b-instruct": 0.9282,
+        "qwen2.5-14b-instruct": 0.8947999999999998,
+        "qwen2.5-32b-instruct": 0.8493999999999999,
+        "qwen2.5-72b-instruct": 0.8458,
+        "llama-3.1-8b-instruct": 1.1641333333333332,
+        "llama-3.1-70b-instruct": 0.8899333333333332,
+        "llama-3.2-3b-instruct": 1.1756666666666669,
+        "llama-3.3-70b-instruct": 0.8181999999999998,
+        "mistral-large-instruct-2411": 0.8889333333333335,
+        "gemma-2-27b-it": 1.1206,
+        "gemma-2-9b-it": 1.2548,
+        "deepseek-v3": 0.937,
+        "deepseek-r1": 0.8470666666666669,
+        "qwq-32b": 0.8959333333333334,
+        "Average": 0.9830266666666666
+    },
+    "GeneticEnv": {
+        "qwen2.5-3b-instruct": 0.8742666666666669,
+        "qwen2.5-7b-instruct": 0.7093333333333331,
+        "qwen2.5-14b-instruct": 0.40293333333333337,
+        "qwen2.5-32b-instruct": 0.44313333333333327,
+        "qwen2.5-72b-instruct": 0.42733333333333323,
+        "llama-3.1-8b-instruct": 0.7788666666666665,
+        "llama-3.1-70b-instruct": 0.39159999999999995,
+        "llama-3.2-3b-instruct": 0.8340666666666667,
+        "llama-3.3-70b-instruct": 0.4035333333333334,
+        "mistral-large-instruct-2411": 0.4183333333333333,
+        "gemma-2-27b-it": 0.4676666666666667,
+        "gemma-2-9b-it": 0.8420000000000002,
+        "deepseek-v3": 0.39733333333333337,
+        "deepseek-r1": 0.3223333333333333,
+        "qwq-32b": 0.4328,
+        "Average": 0.5430355555555555
+    },
+    "CraftsmanEnv": {
+        "qwen2.5-3b-instruct": 0.8531238095238095,
+        "qwen2.5-7b-instruct": 0.8701333333333332,
+        "qwen2.5-14b-instruct": 0.636152380952381,
+        "qwen2.5-32b-instruct": 0.5899619047619048,
+        "qwen2.5-72b-instruct": 0.6157428571428571,
+        "llama-3.1-8b-instruct": 0.906847619047619,
+        "llama-3.1-70b-instruct": 0.6374285714285713,
+        "llama-3.2-3b-instruct": 0.9079333333333333,
+        "llama-3.3-70b-instruct": 0.7432857142857142,
+        "mistral-large-instruct-2411": 0.5945047619047619,
+        "gemma-2-27b-it": 0.8030285714285714,
+        "gemma-2-9b-it": 0.9558666666666668,
+        "deepseek-v3": 0.6411523809523809,
+        "deepseek-r1": 0.572504761904762,
+        "qwq-32b": 0.5707142857142857,
+        "Average": 0.7265587301587301
+    },
+    "StarConstellationEnv": {
+        "qwen2.5-3b-instruct": 0.9018,
+        "qwen2.5-7b-instruct": 0.8849999999999998,
+        "qwen2.5-14b-instruct": 0.6111333333333333,
+        "qwen2.5-32b-instruct": 0.6682,
+        "qwen2.5-72b-instruct": 0.6413333333333333,
+        "llama-3.1-8b-instruct": 0.8276666666666668,
+        "llama-3.1-70b-instruct": 0.6845333333333333,
+        "llama-3.2-3b-instruct": 0.8996666666666666,
+        "llama-3.3-70b-instruct": 0.7238666666666665,
+        "mistral-large-instruct-2411": 0.6063333333333333,
+        "gemma-2-27b-it": 0.6717333333333333,
+        "gemma-2-9b-it": 0.8695999999999999,
+        "deepseek-v3": 0.55,
+        "deepseek-r1": 0.4897333333333334,
+        "qwq-32b": 0.5618000000000001,
+        "Average": 0.7061600000000001
+    },
+    "MythicalCreatureEnv": {
+        "qwen2.5-3b-instruct": 0.9463333333333332,
+        "qwen2.5-7b-instruct": 1.0008666666666666,
+        "qwen2.5-14b-instruct": 0.8189999999999997,
+        "qwen2.5-32b-instruct": 0.7707333333333333,
+        "qwen2.5-72b-instruct": 0.8385333333333334,
+        "llama-3.1-8b-instruct": 1.0950666666666666,
+        "llama-3.1-70b-instruct": 0.7916,
+        "llama-3.2-3b-instruct": 1.1887333333333332,
+        "llama-3.3-70b-instruct": 0.7888666666666666,
+        "mistral-large-instruct-2411": 0.7903999999999999,
+        "gemma-2-27b-it": 0.9704666666666666,
+        "gemma-2-9b-it": 1.1304666666666665,
+        "deepseek-v3": 0.7574,
+        "deepseek-r1": 0.7734,
+        "qwq-32b": 0.7396,
+        "Average": 0.8934311111111112
+    },
+    "ArtStyleEnv": {
+        "qwen2.5-3b-instruct": 0.9593238095238095,
+        "qwen2.5-7b-instruct": 0.8611714285714285,
+        "qwen2.5-14b-instruct": 0.6572000000000001,
+        "qwen2.5-32b-instruct": 0.6888190476190477,
+        "qwen2.5-72b-instruct": 0.6664380952380953,
+        "llama-3.1-8b-instruct": 0.9826952380952381,
+        "llama-3.1-70b-instruct": 0.6773714285714286,
+        "llama-3.2-3b-instruct": 1.0108000000000001,
+        "llama-3.3-70b-instruct": 0.7458571428571428,
+        "mistral-large-instruct-2411": 0.627504761904762,
+        "gemma-2-27b-it": 0.8328380952380952,
+        "gemma-2-9b-it": 1.0002666666666666,
+        "deepseek-v3": 0.723047619047619,
+        "deepseek-r1": 0.666,
+        "qwq-32b": 0.6872952380952381,
+        "Average": 0.7857752380952383
+    },
+    "CookingEnv": {
+        "qwen2.5-3b-instruct": 0.9731333333333332,
+        "qwen2.5-7b-instruct": 0.8531999999999998,
+        "qwen2.5-14b-instruct": 0.6777333333333333,
+        "qwen2.5-32b-instruct": 0.6949333333333334,
+        "qwen2.5-72b-instruct": 0.6868666666666666,
+        "llama-3.1-8b-instruct": 0.9575333333333333,
+        "llama-3.1-70b-instruct": 0.6741333333333334,
+        "llama-3.2-3b-instruct": 0.9920666666666665,
+        "llama-3.3-70b-instruct": 0.7073999999999999,
+        "mistral-large-instruct-2411": 0.6852,
+        "gemma-2-27b-it": 0.8009999999999998,
+        "gemma-2-9b-it": 0.9400666666666666,
+        "deepseek-v3": 0.6910000000000001,
+        "deepseek-r1": 0.6202666666666665,
+        "qwq-32b": 0.5726666666666667,
+        "Average": 0.7684799999999999
+    },
+    "HistoricalBattleEnv": {
+        "qwen2.5-3b-instruct": 0.3906380952380952,
+        "qwen2.5-7b-instruct": 0.39269523809523804,
+        "qwen2.5-14b-instruct": 0.36508571428571424,
+        "qwen2.5-32b-instruct": 0.3839047619047619,
+        "qwen2.5-72b-instruct": 0.37189523809523806,
+        "llama-3.1-8b-instruct": 0.5100190476190476,
+        "llama-3.1-70b-instruct": 0.3623142857142857,
+        "llama-3.2-3b-instruct": 0.5539428571428571,
+        "llama-3.3-70b-instruct": 0.3407428571428571,
+        "mistral-large-instruct-2411": 0.26249523809523806,
+        "gemma-2-27b-it": 0.3749619047619047,
+        "gemma-2-9b-it": 0.4291904761904761,
+        "deepseek-v3": 0.2707428571428572,
+        "deepseek-r1": 0.12205714285714286,
+        "qwq-32b": 0.1069238095238095,
+        "Average": 0.34917396825396824
+    },
+    "FungalEnv": {
+        "qwen2.5-3b-instruct": 0.9867619047619047,
+        "qwen2.5-7b-instruct": 0.7690285714285714,
+        "qwen2.5-14b-instruct": 0.5497523809523809,
+        "qwen2.5-32b-instruct": 0.5654571428571428,
+        "qwen2.5-72b-instruct": 0.5338571428571429,
+        "llama-3.1-8b-instruct": 0.9299904761904761,
+        "llama-3.1-70b-instruct": 0.6940095238095237,
+        "llama-3.2-3b-instruct": 1.0453999999999999,
+        "llama-3.3-70b-instruct": 0.6804285714285714,
+        "mistral-large-instruct-2411": 0.5070380952380952,
+        "gemma-2-27b-it": 0.6260571428571428,
+        "gemma-2-9b-it": 1.0525142857142857,
+        "deepseek-v3": 0.4512380952380953,
+        "deepseek-r1": 0.41535238095238086,
+        "qwq-32b": 0.4612952380952381,
+        "Average": 0.6845453968253967
+    },
+    "CryptographyEnv": {
+        "qwen2.5-3b-instruct": 0.7157333333333333,
+        "qwen2.5-7b-instruct": 0.7917428571428571,
+        "qwen2.5-14b-instruct": 0.5772095238095238,
+        "qwen2.5-32b-instruct": 0.5362666666666666,
+        "qwen2.5-72b-instruct": 0.5816380952380952,
+        "llama-3.1-8b-instruct": 0.7762666666666667,
+        "llama-3.1-70b-instruct": 0.5880761904761905,
+        "llama-3.2-3b-instruct": 0.9222476190476192,
+        "llama-3.3-70b-instruct": 0.6200666666666668,
+        "mistral-large-instruct-2411": 0.43243809523809523,
+        "gemma-2-27b-it": 0.6965333333333332,
+        "gemma-2-9b-it": 0.9170952380952381,
+        "deepseek-v3": 0.4242190476190476,
+        "deepseek-r1": 0.31665714285714286,
+        "qwq-32b": 0.3307142857142857,
+        "Average": 0.6151269841269841
+    },
+    "StorageEnv": {
+        "qwen2.5-3b-instruct": 0.5999999999999999,
+        "qwen2.5-7b-instruct": 0.5174666666666666,
+        "qwen2.5-14b-instruct": 0.26799999999999996,
+        "qwen2.5-32b-instruct": 0.3171333333333333,
+        "qwen2.5-72b-instruct": 0.30706666666666665,
+        "llama-3.1-8b-instruct": 0.6547333333333333,
+        "llama-3.1-70b-instruct": 0.3390666666666667,
+        "llama-3.2-3b-instruct": 0.6575333333333333,
+        "llama-3.3-70b-instruct": 0.2899333333333334,
+        "mistral-large-instruct-2411": 0.28440000000000004,
+        "gemma-2-27b-it": 0.4133333333333333,
+        "gemma-2-9b-it": 0.5988666666666667,
+        "deepseek-v3": 0.34040000000000004,
+        "deepseek-r1": 0.3333333333333333,
+        "qwq-32b": 0.33946666666666664,
+        "Average": 0.41738222222222215
+    },
+    "RoverEnv": {
+        "qwen2.5-3b-instruct": 0.9546666666666667,
+        "qwen2.5-7b-instruct": 1.0193333333333334,
+        "qwen2.5-14b-instruct": 0.5934,
+        "qwen2.5-32b-instruct": 0.6414,
+        "qwen2.5-72b-instruct": 0.5923999999999999,
+        "llama-3.1-8b-instruct": 0.9858666666666667,
+        "llama-3.1-70b-instruct": 0.7111333333333333,
+        "llama-3.2-3b-instruct": 1.0410666666666666,
+        "llama-3.3-70b-instruct": 0.6332666666666666,
+        "mistral-large-instruct-2411": 0.7143999999999999,
+        "gemma-2-27b-it": 0.7877333333333333,
+        "gemma-2-9b-it": 1.0685333333333333,
+        "deepseek-v3": 0.7905333333333333,
+        "deepseek-r1": 0.7494,
+        "qwq-32b": 0.7479333333333333,
+        "Average": 0.8020711111111112
+    },
+    "FashionEnv": {
+        "qwen2.5-3b-instruct": 1.0357333333333334,
+        "qwen2.5-7b-instruct": 1.081152380952381,
+        "qwen2.5-14b-instruct": 0.7285238095238096,
+        "qwen2.5-32b-instruct": 0.7431523809523809,
+        "qwen2.5-72b-instruct": 0.7598666666666667,
+        "llama-3.1-8b-instruct": 1.0961333333333332,
+        "llama-3.1-70b-instruct": 0.8041333333333333,
+        "llama-3.2-3b-instruct": 1.1326571428571426,
+        "llama-3.3-70b-instruct": 0.8184666666666667,
+        "mistral-large-instruct-2411": 0.8105238095238094,
+        "gemma-2-27b-it": 0.9382190476190475,
+        "gemma-2-9b-it": 1.0972,
+        "deepseek-v3": 0.8063809523809524,
+        "deepseek-r1": 0.7738476190476191,
+        "qwq-32b": 0.8007333333333335,
+        "Average": 0.8951149206349207
+    },
+    "LicenseEnv": {
+        "qwen2.5-3b-instruct": 0.7847999999999999,
+        "qwen2.5-7b-instruct": 0.8215333333333333,
+        "qwen2.5-14b-instruct": 0.6174666666666666,
+        "qwen2.5-32b-instruct": 0.7098666666666666,
+        "qwen2.5-72b-instruct": 0.7198666666666667,
+        "llama-3.1-8b-instruct": 0.8523333333333334,
+        "llama-3.1-70b-instruct": 0.6513333333333332,
+        "llama-3.2-3b-instruct": 0.9648666666666668,
+        "llama-3.3-70b-instruct": 0.6662000000000001,
+        "mistral-large-instruct-2411": 0.6437333333333333,
+        "gemma-2-27b-it": 0.7512666666666666,
+        "gemma-2-9b-it": 0.8070666666666666,
+        "deepseek-v3": 0.6174666666666666,
+        "deepseek-r1": 0.5982666666666666,
+        "qwq-32b": 0.6115999999999999,
+        "Average": 0.7211777777777777
+    },
+    "VirusClassificationEnv": {
+        "qwen2.5-3b-instruct": 0.5887238095238095,
+        "qwen2.5-7b-instruct": 0.6255999999999999,
+        "qwen2.5-14b-instruct": 0.43513333333333326,
+        "qwen2.5-32b-instruct": 0.4164,
+        "qwen2.5-72b-instruct": 0.39893333333333336,
+        "llama-3.1-8b-instruct": 0.6247333333333334,
+        "llama-3.1-70b-instruct": 0.5219333333333334,
+        "llama-3.2-3b-instruct": 0.6386095238095237,
+        "llama-3.3-70b-instruct": 0.4547333333333333,
+        "mistral-large-instruct-2411": 0.3114571428571429,
+        "gemma-2-27b-it": 0.48719999999999997,
+        "gemma-2-9b-it": 0.6325809523809524,
+        "deepseek-v3": 0.30473333333333336,
+        "deepseek-r1": 0.2137142857142857,
+        "qwq-32b": 0.22217142857142855,
+        "Average": 0.45844380952380953
+    },
+    "TestingEnv": {
+        "qwen2.5-3b-instruct": 0.5297333333333333,
+        "qwen2.5-7b-instruct": 0.5164666666666667,
+        "qwen2.5-14b-instruct": 0.4224666666666666,
+        "qwen2.5-32b-instruct": 0.4540666666666667,
+        "qwen2.5-72b-instruct": 0.39493333333333325,
+        "llama-3.1-8b-instruct": 0.5270666666666667,
+        "llama-3.1-70b-instruct": 0.3365333333333333,
+        "llama-3.2-3b-instruct": 0.5638666666666666,
+        "llama-3.3-70b-instruct": 0.39473333333333327,
+        "mistral-large-instruct-2411": 0.3972,
+        "gemma-2-27b-it": 0.5658,
+        "gemma-2-9b-it": 0.6542,
+        "deepseek-v3": 0.37939999999999996,
+        "deepseek-r1": 0.25579999999999997,
+        "qwq-32b": 0.3352,
+        "Average": 0.44849777777777783
+    },
+    "NarrativeDetectEnv": {
+        "qwen2.5-3b-instruct": 1.0932666666666666,
+        "qwen2.5-7b-instruct": 0.9698666666666667,
+        "qwen2.5-14b-instruct": 0.8831333333333333,
+        "qwen2.5-32b-instruct": 0.7640666666666666,
+        "qwen2.5-72b-instruct": 0.8158000000000001,
+        "llama-3.1-8b-instruct": 1.0600666666666667,
+        "llama-3.1-70b-instruct": 0.8113999999999999,
+        "llama-3.2-3b-instruct": 1.2458666666666667,
+        "llama-3.3-70b-instruct": 0.8439333333333334,
+        "mistral-large-instruct-2411": 0.8011333333333333,
+        "gemma-2-27b-it": 1.0462666666666665,
+        "gemma-2-9b-it": 1.0814666666666668,
+        "deepseek-v3": 0.9039333333333334,
+        "deepseek-r1": 0.82,
+        "qwq-32b": 0.8263999999999999,
+        "Average": 0.9311066666666665
+    },
+    "RenewableEnergyEnv": {
+        "qwen2.5-3b-instruct": 1.2372,
+        "qwen2.5-7b-instruct": 1.209,
+        "qwen2.5-14b-instruct": 1.018,
+        "qwen2.5-32b-instruct": 0.8681999999999999,
+        "qwen2.5-72b-instruct": 0.8295333333333333,
+        "llama-3.1-8b-instruct": 1.3595333333333333,
+        "llama-3.1-70b-instruct": 0.8166666666666667,
+        "llama-3.2-3b-instruct": 1.2722666666666664,
+        "llama-3.3-70b-instruct": 0.9336000000000002,
+        "mistral-large-instruct-2411": 0.8966666666666667,
+        "gemma-2-27b-it": 1.2019333333333333,
+        "gemma-2-9b-it": 1.3341999999999998,
+        "deepseek-v3": 0.898,
+        "deepseek-r1": 0.8659333333333334,
+        "qwq-32b": 0.9053333333333334,
+        "Average": 1.043071111111111
+    },
+    "CelestialEnv": {
+        "qwen2.5-3b-instruct": 0.8438666666666667,
+        "qwen2.5-7b-instruct": 0.8887999999999998,
+        "qwen2.5-14b-instruct": 0.6514,
+        "qwen2.5-32b-instruct": 0.6459333333333334,
+        "qwen2.5-72b-instruct": 0.6326666666666666,
+        "llama-3.1-8b-instruct": 0.9612666666666666,
+        "llama-3.1-70b-instruct": 0.6192,
+        "llama-3.2-3b-instruct": 0.8965333333333334,
+        "llama-3.3-70b-instruct": 0.6164,
+        "mistral-large-instruct-2411": 0.6203333333333334,
+        "gemma-2-27b-it": 0.7378,
+        "gemma-2-9b-it": 0.9489333333333333,
+        "deepseek-v3": 0.6561999999999999,
+        "deepseek-r1": 0.5421333333333334,
+        "qwq-32b": 0.5784666666666667,
+        "Average": 0.7226622222222223
+    },
+    "SpiceEnv": {
+        "qwen2.5-3b-instruct": 0.6036476190476192,
+        "qwen2.5-7b-instruct": 0.6609809523809524,
+        "qwen2.5-14b-instruct": 0.40272380952380954,
+        "qwen2.5-32b-instruct": 0.5753809523809524,
+        "qwen2.5-72b-instruct": 0.46193333333333336,
+        "llama-3.1-8b-instruct": 0.6512666666666667,
+        "llama-3.1-70b-instruct": 0.5352666666666666,
+        "llama-3.2-3b-instruct": 0.6274,
+        "llama-3.3-70b-instruct": 0.594,
+        "mistral-large-instruct-2411": 0.45503809523809513,
+        "gemma-2-27b-it": 0.6168666666666667,
+        "gemma-2-9b-it": 0.7341333333333334,
+        "deepseek-v3": 0.31380952380952376,
+        "deepseek-r1": 0.36774285714285704,
+        "qwq-32b": 0.37498095238095236,
+        "Average": 0.5316780952380953
+    },
+    "WildlifeEnv": {
+        "qwen2.5-3b-instruct": 0.7888,
+        "qwen2.5-7b-instruct": 0.7621333333333333,
+        "qwen2.5-14b-instruct": 0.6147999999999999,
+        "qwen2.5-32b-instruct": 0.7297333333333332,
+        "qwen2.5-72b-instruct": 0.6115999999999999,
+        "llama-3.1-8b-instruct": 0.8686666666666666,
+        "llama-3.1-70b-instruct": 0.6302,
+        "llama-3.2-3b-instruct": 0.7972666666666667,
+        "llama-3.3-70b-instruct": 0.6359999999999999,
+        "mistral-large-instruct-2411": 0.6615333333333333,
+        "gemma-2-27b-it": 0.7294666666666667,
+        "gemma-2-9b-it": 0.8138666666666665,
+        "deepseek-v3": 0.6534000000000001,
+        "deepseek-r1": 0.7072666666666667,
+        "qwq-32b": 0.7271333333333333,
+        "Average": 0.7154577777777777
+    },
+    "VehicleEnv": {
+        "qwen2.5-3b-instruct": 0.9630666666666666,
+        "qwen2.5-7b-instruct": 0.9056000000000001,
+        "qwen2.5-14b-instruct": 0.7067333333333332,
+        "qwen2.5-32b-instruct": 0.5080666666666666,
+        "qwen2.5-72b-instruct": 0.4952666666666666,
+        "llama-3.1-8b-instruct": 1.0144666666666668,
+        "llama-3.1-70b-instruct": 0.6701333333333334,
+        "llama-3.2-3b-instruct": 1.0123333333333333,
+        "llama-3.3-70b-instruct": 0.6127333333333332,
+        "mistral-large-instruct-2411": 0.37593333333333334,
+        "gemma-2-27b-it": 0.7358666666666668,
+        "gemma-2-9b-it": 1.0004666666666666,
+        "deepseek-v3": 0.38853333333333334,
+        "deepseek-r1": 0.30946666666666667,
+        "qwq-32b": 0.3487333333333333,
+        "Average": 0.6698266666666667
+    },
+    "BeverageEnv": {
+        "qwen2.5-3b-instruct": 1.1309999999999998,
+        "qwen2.5-7b-instruct": 1.0566666666666666,
+        "qwen2.5-14b-instruct": 0.7231333333333334,
+        "qwen2.5-32b-instruct": 0.8653333333333334,
+        "qwen2.5-72b-instruct": 0.8098666666666666,
+        "llama-3.1-8b-instruct": 1.0646666666666664,
+        "llama-3.1-70b-instruct": 0.7819333333333334,
+        "llama-3.2-3b-instruct": 1.0867999999999998,
+        "llama-3.3-70b-instruct": 0.8621333333333332,
+        "mistral-large-instruct-2411": 0.8074666666666666,
+        "gemma-2-27b-it": 0.9830666666666668,
+        "gemma-2-9b-it": 1.0837999999999999,
+        "deepseek-v3": 0.7968,
+        "deepseek-r1": 0.7807333333333334,
+        "qwq-32b": 0.7677333333333334,
+        "Average": 0.9067422222222222
+    },
+    "ControlEnv": {
+        "qwen2.5-3b-instruct": 1.2409333333333332,
+        "qwen2.5-7b-instruct": 1.1129999999999998,
+        "qwen2.5-14b-instruct": 0.9396000000000001,
+        "qwen2.5-32b-instruct": 0.9234,
+        "qwen2.5-72b-instruct": 0.8239333333333333,
+        "llama-3.1-8b-instruct": 1.1922666666666668,
+        "llama-3.1-70b-instruct": 0.8639999999999999,
+        "llama-3.2-3b-instruct": 1.1910666666666665,
+        "llama-3.3-70b-instruct": 0.9382666666666666,
+        "mistral-large-instruct-2411": 0.9432666666666666,
+        "gemma-2-27b-it": 1.0350666666666668,
+        "gemma-2-9b-it": 1.3362,
+        "deepseek-v3": 0.8779333333333333,
+        "deepseek-r1": 0.8366666666666667,
+        "qwq-32b": 0.8624666666666666,
+        "Average": 1.007871111111111
+    },
+    "CurrencyEnv": {
+        "qwen2.5-3b-instruct": 1.1619999999999997,
+        "qwen2.5-7b-instruct": 1.1104666666666667,
+        "qwen2.5-14b-instruct": 1.0066666666666666,
+        "qwen2.5-32b-instruct": 0.9369333333333332,
+        "qwen2.5-72b-instruct": 0.9753999999999999,
+        "llama-3.1-8b-instruct": 1.2676666666666667,
+        "llama-3.1-70b-instruct": 0.8947999999999998,
+        "llama-3.2-3b-instruct": 1.261,
+        "llama-3.3-70b-instruct": 0.9674666666666665,
+        "mistral-large-instruct-2411": 0.8869999999999998,
+        "gemma-2-27b-it": 1.0257333333333334,
+        "gemma-2-9b-it": 1.3512,
+        "deepseek-v3": 0.9630666666666666,
+        "deepseek-r1": 0.8782666666666665,
+        "qwq-32b": 0.9007999999999999,
+        "Average": 1.0392311111111112
+    },
+    "MarketingEnv": {
+        "qwen2.5-3b-instruct": 0.7427333333333332,
+        "qwen2.5-7b-instruct": 0.6565333333333332,
+        "qwen2.5-14b-instruct": 0.6416000000000001,
+        "qwen2.5-32b-instruct": 0.5615333333333333,
+        "qwen2.5-72b-instruct": 0.5475333333333334,
+        "llama-3.1-8b-instruct": 0.7419999999999999,
+        "llama-3.1-70b-instruct": 0.5211333333333333,
+        "llama-3.2-3b-instruct": 0.7737333333333333,
+        "llama-3.3-70b-instruct": 0.5229999999999999,
+        "mistral-large-instruct-2411": 0.5469999999999999,
+        "gemma-2-27b-it": 0.7222000000000001,
+        "gemma-2-9b-it": 0.8039333333333334,
+        "deepseek-v3": 0.6286666666666666,
+        "deepseek-r1": 0.5670666666666666,
+        "qwq-32b": 0.5600666666666666,
+        "Average": 0.6359155555555555
+    },
+    "BotanicalEnv": {
+        "qwen2.5-3b-instruct": 1.3478666666666668,
+        "qwen2.5-7b-instruct": 1.3568,
+        "qwen2.5-14b-instruct": 0.7390000000000001,
+        "qwen2.5-32b-instruct": 0.9401333333333334,
+        "qwen2.5-72b-instruct": 0.8344666666666665,
+        "llama-3.1-8b-instruct": 1.3095999999999999,
+        "llama-3.1-70b-instruct": 0.8597999999999999,
+        "llama-3.2-3b-instruct": 1.2815999999999999,
+        "llama-3.3-70b-instruct": 0.9140666666666665,
+        "mistral-large-instruct-2411": 0.8783333333333333,
+        "gemma-2-27b-it": 1.0331333333333332,
+        "gemma-2-9b-it": 1.4613999999999998,
+        "deepseek-v3": 0.8467333333333332,
+        "deepseek-r1": 0.6417333333333334,
+        "qwq-32b": 0.6957333333333333,
+        "Average": 1.00936
+    },
+    "CircusActEnv": {
+        "qwen2.5-3b-instruct": 0.966,
+        "qwen2.5-7b-instruct": 0.8732666666666665,
+        "qwen2.5-14b-instruct": 0.7160666666666667,
+        "qwen2.5-32b-instruct": 0.6424000000000001,
+        "qwen2.5-72b-instruct": 0.6185333333333333,
+        "llama-3.1-8b-instruct": 1.0588000000000002,
+        "llama-3.1-70b-instruct": 0.6578,
+        "llama-3.2-3b-instruct": 1.0192666666666663,
+        "llama-3.3-70b-instruct": 0.6707333333333333,
+        "mistral-large-instruct-2411": 0.5906,
+        "gemma-2-27b-it": 0.8663333333333334,
+        "gemma-2-9b-it": 0.9901333333333333,
+        "deepseek-v3": 0.6095333333333334,
+        "deepseek-r1": 0.5542666666666667,
+        "qwq-32b": 0.612,
+        "Average": 0.7630488888888889
+    },
+    "AudioDialectEnv": {
+        "qwen2.5-3b-instruct": 1.1560666666666666,
+        "qwen2.5-7b-instruct": 1.1981333333333333,
+        "qwen2.5-14b-instruct": 0.9919333333333332,
+        "qwen2.5-32b-instruct": 0.9843999999999999,
+        "qwen2.5-72b-instruct": 1.0026,
+        "llama-3.1-8b-instruct": 1.1826,
+        "llama-3.1-70b-instruct": 1.049,
+        "llama-3.2-3b-instruct": 1.2086666666666668,
+        "llama-3.3-70b-instruct": 1.1178666666666666,
+        "mistral-large-instruct-2411": 0.9938666666666667,
+        "gemma-2-27b-it": 1.1272666666666669,
+        "gemma-2-9b-it": 1.255666666666667,
+        "deepseek-v3": 0.9454666666666667,
+        "deepseek-r1": 0.8542666666666667,
+        "qwq-32b": 0.9452,
+        "Average": 1.0675333333333334
+    },
+    "LeadershipEnv": {
+        "qwen2.5-3b-instruct": 1.1378,
+        "qwen2.5-7b-instruct": 1.1529333333333334,
+        "qwen2.5-14b-instruct": 0.9892285714285715,
+        "qwen2.5-32b-instruct": 1.036095238095238,
+        "qwen2.5-72b-instruct": 0.9751333333333333,
+        "llama-3.1-8b-instruct": 1.2512571428571426,
+        "llama-3.1-70b-instruct": 0.9471428571428572,
+        "llama-3.2-3b-instruct": 1.450133333333333,
+        "llama-3.3-70b-instruct": 1.0285999999999997,
+        "mistral-large-instruct-2411": 0.9162380952380952,
+        "gemma-2-27b-it": 1.2164380952380953,
+        "gemma-2-9b-it": 1.3166761904761903,
+        "deepseek-v3": 0.9108571428571428,
+        "deepseek-r1": 0.9028190476190476,
+        "qwq-32b": 0.8550952380952381,
+        "Average": 1.0724298412698412
+    },
+    "TransportEnv": {
+        "qwen2.5-3b-instruct": 0.7256761904761905,
+        "qwen2.5-7b-instruct": 0.6674,
+        "qwen2.5-14b-instruct": 0.425752380952381,
+        "qwen2.5-32b-instruct": 0.5705047619047618,
+        "qwen2.5-72b-instruct": 0.4020666666666667,
+        "llama-3.1-8b-instruct": 0.7760380952380952,
+        "llama-3.1-70b-instruct": 0.5022666666666666,
+        "llama-3.2-3b-instruct": 0.8045333333333333,
+        "llama-3.3-70b-instruct": 0.5512285714285714,
+        "mistral-large-instruct-2411": 0.4226571428571429,
+        "gemma-2-27b-it": 0.6612190476190476,
+        "gemma-2-9b-it": 0.7567999999999999,
+        "deepseek-v3": 0.4245333333333333,
+        "deepseek-r1": 0.35583809523809523,
+        "qwq-32b": 0.42556190476190475,
+        "Average": 0.5648050793650794
+    },
+    "EcologicalEnv": {
+        "qwen2.5-3b-instruct": 0.5565333333333333,
+        "qwen2.5-7b-instruct": 0.3861333333333333,
+        "qwen2.5-14b-instruct": 0.23986666666666662,
+        "qwen2.5-32b-instruct": 0.2175333333333333,
+        "qwen2.5-72b-instruct": 0.2650666666666667,
+        "llama-3.1-8b-instruct": 0.5481333333333334,
+        "llama-3.1-70b-instruct": 0.27026666666666666,
+        "llama-3.2-3b-instruct": 0.5608666666666666,
+        "llama-3.3-70b-instruct": 0.34073333333333333,
+        "mistral-large-instruct-2411": 0.18666666666666668,
+        "gemma-2-27b-it": 0.3159333333333333,
+        "gemma-2-9b-it": 0.49386666666666673,
+        "deepseek-v3": 0.25439999999999996,
+        "deepseek-r1": 0.13513333333333333,
+        "qwq-32b": 0.1812,
+        "Average": 0.3301555555555555
+    },
+    "MythicEnv": {
+        "qwen2.5-3b-instruct": 1.1101999999999999,
+        "qwen2.5-7b-instruct": 0.9876000000000001,
+        "qwen2.5-14b-instruct": 0.7183999999999999,
+        "qwen2.5-32b-instruct": 0.8451333333333334,
+        "qwen2.5-72b-instruct": 0.7776666666666666,
+        "llama-3.1-8b-instruct": 1.1285333333333334,
+        "llama-3.1-70b-instruct": 0.8145999999999999,
+        "llama-3.2-3b-instruct": 1.2702,
+        "llama-3.3-70b-instruct": 0.8547333333333332,
+        "mistral-large-instruct-2411": 0.7791333333333332,
+        "gemma-2-27b-it": 0.9578666666666666,
+        "gemma-2-9b-it": 1.1880000000000002,
+        "deepseek-v3": 0.7562,
+        "deepseek-r1": 0.628,
+        "qwq-32b": 0.7259333333333334,
+        "Average": 0.9028133333333334
+    },
+    "EnzymeEnv": {
+        "qwen2.5-3b-instruct": 0.5272666666666666,
+        "qwen2.5-7b-instruct": 0.5749999999999998,
+        "qwen2.5-14b-instruct": 0.45233333333333325,
+        "qwen2.5-32b-instruct": 0.44746666666666657,
+        "qwen2.5-72b-instruct": 0.4640666666666666,
+        "llama-3.1-8b-instruct": 0.6982666666666667,
+        "llama-3.1-70b-instruct": 0.4665333333333333,
+        "llama-3.2-3b-instruct": 0.7106666666666666,
+        "llama-3.3-70b-instruct": 0.4798,
+        "mistral-large-instruct-2411": 0.425,
+        "gemma-2-27b-it": 0.5391999999999999,
+        "gemma-2-9b-it": 0.6941333333333333,
+        "deepseek-v3": 0.37926666666666664,
+        "deepseek-r1": 0.38086666666666663,
+        "qwq-32b": 0.4045333333333333,
+        "Average": 0.5096266666666667
+    },
+    "OSKernelEnv": {
+        "qwen2.5-3b-instruct": 1.1656,
+        "qwen2.5-7b-instruct": 1.3032,
+        "qwen2.5-14b-instruct": 0.8570666666666666,
+        "qwen2.5-32b-instruct": 0.8768666666666667,
+        "qwen2.5-72b-instruct": 0.8728,
+        "llama-3.1-8b-instruct": 1.184,
+        "llama-3.1-70b-instruct": 0.8322666666666667,
+        "llama-3.2-3b-instruct": 1.3510000000000002,
+        "llama-3.3-70b-instruct": 0.8083333333333333,
+        "mistral-large-instruct-2411": 0.8513333333333332,
+        "gemma-2-27b-it": 1.0258666666666667,
+        "gemma-2-9b-it": 1.3057333333333332,
+        "deepseek-v3": 0.8445333333333332,
+        "deepseek-r1": 0.7511333333333332,
+        "qwq-32b": 0.8475333333333334,
+        "Average": 0.9918177777777777
+    },
+    "MineralClassificationEnv": {
+        "qwen2.5-3b-instruct": 1.0583333333333333,
+        "qwen2.5-7b-instruct": 1.0704666666666667,
+        "qwen2.5-14b-instruct": 0.7609999999999999,
+        "qwen2.5-32b-instruct": 0.7188666666666668,
+        "qwen2.5-72b-instruct": 0.6955333333333333,
+        "llama-3.1-8b-instruct": 1.1152000000000002,
+        "llama-3.1-70b-instruct": 0.6619333333333334,
+        "llama-3.2-3b-instruct": 1.1165333333333334,
+        "llama-3.3-70b-instruct": 0.6672666666666666,
+        "mistral-large-instruct-2411": 0.7607333333333333,
+        "gemma-2-27b-it": 0.9294,
+        "gemma-2-9b-it": 1.2250666666666667,
+        "deepseek-v3": 0.8092,
+        "deepseek-r1": 0.7899999999999999,
+        "qwq-32b": 0.7879333333333334,
+        "Average": 0.8778311111111109
+    },
+    "EconomicEnv": {
+        "qwen2.5-3b-instruct": 1.1286,
+        "qwen2.5-7b-instruct": 1.16,
+        "qwen2.5-14b-instruct": 0.8704666666666666,
+        "qwen2.5-32b-instruct": 0.8274666666666667,
+        "qwen2.5-72b-instruct": 0.7895333333333333,
+        "llama-3.1-8b-instruct": 1.1526666666666667,
+        "llama-3.1-70b-instruct": 0.7768,
+        "llama-3.2-3b-instruct": 1.1796666666666666,
+        "llama-3.3-70b-instruct": 0.8427333333333333,
+        "mistral-large-instruct-2411": 0.8880666666666667,
+        "gemma-2-27b-it": 1.0978666666666665,
+        "gemma-2-9b-it": 1.4352000000000003,
+        "deepseek-v3": 0.9310666666666668,
+        "deepseek-r1": 0.8318000000000001,
+        "qwq-32b": 0.8415333333333332,
+        "Average": 0.9835644444444444
+    },
+    "DetectiveEnv": {
+        "qwen2.5-3b-instruct": 0.9592666666666666,
+        "qwen2.5-7b-instruct": 0.8579333333333332,
+        "qwen2.5-14b-instruct": 0.5528666666666666,
+        "qwen2.5-32b-instruct": 0.6906666666666667,
+        "qwen2.5-72b-instruct": 0.6596,
+        "llama-3.1-8b-instruct": 1.0208666666666666,
+        "llama-3.1-70b-instruct": 0.7068,
+        "llama-3.2-3b-instruct": 1.0127333333333335,
+        "llama-3.3-70b-instruct": 0.7222666666666665,
+        "mistral-large-instruct-2411": 0.6398666666666667,
+        "gemma-2-27b-it": 1.0352000000000001,
+        "gemma-2-9b-it": 1.2517999999999998,
+        "deepseek-v3": 0.6811999999999999,
+        "deepseek-r1": 0.6839333333333333,
+        "qwq-32b": 0.6996,
+        "Average": 0.81164
+    },
+    "ChessEnv": {
+        "qwen2.5-3b-instruct": 0.9558666666666668,
+        "qwen2.5-7b-instruct": 1.0245333333333335,
+        "qwen2.5-14b-instruct": 0.8131333333333333,
+        "qwen2.5-32b-instruct": 0.8892,
+        "qwen2.5-72b-instruct": 0.8331999999999999,
+        "llama-3.1-8b-instruct": 1.1225333333333334,
+        "llama-3.1-70b-instruct": 0.7468666666666667,
+        "llama-3.2-3b-instruct": 1.1218,
+        "llama-3.3-70b-instruct": 0.8098666666666666,
+        "mistral-large-instruct-2411": 0.7781333333333335,
+        "gemma-2-27b-it": 1.01,
+        "gemma-2-9b-it": 1.2222666666666666,
+        "deepseek-v3": 0.7901333333333332,
+        "deepseek-r1": 0.7748,
+        "qwq-32b": 0.8231333333333334,
+        "Average": 0.9143644444444444
+    },
+    "MythicalEnv": {
+        "qwen2.5-3b-instruct": 0.9932000000000001,
+        "qwen2.5-7b-instruct": 1.0899333333333334,
+        "qwen2.5-14b-instruct": 0.7302,
+        "qwen2.5-32b-instruct": 0.8645999999999999,
+        "qwen2.5-72b-instruct": 0.8496666666666666,
+        "llama-3.1-8b-instruct": 1.0838,
+        "llama-3.1-70b-instruct": 0.8592000000000001,
+        "llama-3.2-3b-instruct": 1.0404666666666667,
+        "llama-3.3-70b-instruct": 0.8421333333333333,
+        "mistral-large-instruct-2411": 0.8762666666666666,
+        "gemma-2-27b-it": 0.8621333333333334,
+        "gemma-2-9b-it": 1.0032,
+        "deepseek-v3": 0.885,
+        "deepseek-r1": 0.7668000000000001,
+        "qwq-32b": 0.8260000000000002,
+        "Average": 0.90484
+    },
+    "ChemicalCompoundsEnv": {
+        "qwen2.5-3b-instruct": 0.8311047619047619,
+        "qwen2.5-7b-instruct": 0.8545238095238095,
+        "qwen2.5-14b-instruct": 0.6625238095238095,
+        "qwen2.5-32b-instruct": 0.7971619047619047,
+        "qwen2.5-72b-instruct": 0.7787238095238094,
+        "llama-3.1-8b-instruct": 0.9210666666666665,
+        "llama-3.1-70b-instruct": 0.8095619047619046,
+        "llama-3.2-3b-instruct": 0.870647619047619,
+        "llama-3.3-70b-instruct": 0.8861619047619047,
+        "mistral-large-instruct-2411": 0.665295238095238,
+        "gemma-2-27b-it": 0.8178285714285713,
+        "gemma-2-9b-it": 0.9217333333333333,
+        "deepseek-v3": 0.6765047619047617,
+        "deepseek-r1": 0.4232571428571429,
+        "qwq-32b": 0.41698095238095234,
+        "Average": 0.7555384126984125
+    },
+    "ArchitecturalEnv": {
+        "qwen2.5-3b-instruct": 0.8535333333333333,
+        "qwen2.5-7b-instruct": 0.9366666666666668,
+        "qwen2.5-14b-instruct": 0.6431333333333333,
+        "qwen2.5-32b-instruct": 0.7234666666666666,
+        "qwen2.5-72b-instruct": 0.6861333333333335,
+        "llama-3.1-8b-instruct": 0.9704666666666666,
+        "llama-3.1-70b-instruct": 0.769,
+        "llama-3.2-3b-instruct": 1.0212666666666665,
+        "llama-3.3-70b-instruct": 0.8717333333333332,
+        "mistral-large-instruct-2411": 0.6912,
+        "gemma-2-27b-it": 0.8425333333333332,
+        "gemma-2-9b-it": 1.0264,
+        "deepseek-v3": 0.6093333333333333,
+        "deepseek-r1": 0.6285333333333333,
+        "qwq-32b": 0.6964,
+        "Average": 0.7979866666666668
+    },
+    "ComputationEnv": {
+        "qwen2.5-3b-instruct": 0.9820666666666668,
+        "qwen2.5-7b-instruct": 0.9801333333333334,
+        "qwen2.5-14b-instruct": 0.7334666666666666,
+        "qwen2.5-32b-instruct": 0.6850666666666666,
+        "qwen2.5-72b-instruct": 0.6938000000000001,
+        "llama-3.1-8b-instruct": 1.0237333333333332,
+        "llama-3.1-70b-instruct": 0.6686,
+        "llama-3.2-3b-instruct": 1.0106666666666666,
+        "llama-3.3-70b-instruct": 0.6860666666666666,
+        "mistral-large-instruct-2411": 0.7517333333333334,
+        "gemma-2-27b-it": 0.8299999999999998,
+        "gemma-2-9b-it": 1.0842666666666667,
+        "deepseek-v3": 0.7249999999999999,
+        "deepseek-r1": 0.7374666666666667,
+        "qwq-32b": 0.7521999999999999,
+        "Average": 0.8229511111111111
+    },
+    "MachinePartEnv": {
+        "qwen2.5-3b-instruct": 0.9062666666666666,
+        "qwen2.5-7b-instruct": 0.8395333333333334,
+        "qwen2.5-14b-instruct": 0.6237999999999999,
+        "qwen2.5-32b-instruct": 0.6204666666666667,
+        "qwen2.5-72b-instruct": 0.6410666666666667,
+        "llama-3.1-8b-instruct": 0.8998666666666665,
+        "llama-3.1-70b-instruct": 0.5422666666666667,
+        "llama-3.2-3b-instruct": 0.9272,
+        "llama-3.3-70b-instruct": 0.5463333333333333,
+        "mistral-large-instruct-2411": 0.5808,
+        "gemma-2-27b-it": 0.6800666666666666,
+        "gemma-2-9b-it": 0.9401999999999997,
+        "deepseek-v3": 0.6576,
+        "deepseek-r1": 0.6320666666666666,
+        "qwq-32b": 0.5902,
+        "Average": 0.7085155555555555
+    },
+    "LiteraryEnv": {
+        "qwen2.5-3b-instruct": 0.7915619047619047,
+        "qwen2.5-7b-instruct": 0.684247619047619,
+        "qwen2.5-14b-instruct": 0.4320857142857143,
+        "qwen2.5-32b-instruct": 0.47454285714285704,
+        "qwen2.5-72b-instruct": 0.45714285714285713,
+        "llama-3.1-8b-instruct": 0.7595047619047619,
+        "llama-3.1-70b-instruct": 0.5143047619047618,
+        "llama-3.2-3b-instruct": 0.8008476190476189,
+        "llama-3.3-70b-instruct": 0.5506952380952381,
+        "mistral-large-instruct-2411": 0.5536571428571427,
+        "gemma-2-27b-it": 0.6854666666666664,
+        "gemma-2-9b-it": 0.8457333333333332,
+        "deepseek-v3": 0.5392285714285714,
+        "deepseek-r1": 0.5025047619047619,
+        "qwq-32b": 0.4939333333333332,
+        "Average": 0.6056971428571427
+    },
+    "MarineEnv": {
+        "qwen2.5-3b-instruct": 1.0838666666666668,
+        "qwen2.5-7b-instruct": 1.0142666666666666,
+        "qwen2.5-14b-instruct": 0.7625333333333334,
+        "qwen2.5-32b-instruct": 0.7773333333333333,
+        "qwen2.5-72b-instruct": 0.8016666666666667,
+        "llama-3.1-8b-instruct": 1.1154666666666668,
+        "llama-3.1-70b-instruct": 0.8399333333333333,
+        "llama-3.2-3b-instruct": 1.1426000000000003,
+        "llama-3.3-70b-instruct": 0.8375999999999999,
+        "mistral-large-instruct-2411": 0.8630666666666666,
+        "gemma-2-27b-it": 0.9411333333333334,
+        "gemma-2-9b-it": 1.1442,
+        "deepseek-v3": 0.8894666666666666,
+        "deepseek-r1": 0.8458,
+        "qwq-32b": 0.8745333333333333,
+        "Average": 0.9288977777777778
+    },
+    "PhilosophyEnv": {
+        "qwen2.5-3b-instruct": 1.05,
+        "qwen2.5-7b-instruct": 1.3602666666666665,
+        "qwen2.5-14b-instruct": 0.6244,
+        "qwen2.5-32b-instruct": 0.6048,
+        "qwen2.5-72b-instruct": 0.6090666666666666,
+        "llama-3.1-8b-instruct": 1.0042666666666666,
+        "llama-3.1-70b-instruct": 0.6868,
+        "llama-3.2-3b-instruct": 1.2236666666666667,
+        "llama-3.3-70b-instruct": 0.6848666666666666,
+        "mistral-large-instruct-2411": 0.5620666666666667,
+        "gemma-2-27b-it": 0.9582,
+        "gemma-2-9b-it": 0.9566666666666667,
+        "deepseek-v3": 0.5928666666666667,
+        "deepseek-r1": 0.5505333333333333,
+        "qwq-32b": 0.5388666666666666,
+        "Average": 0.800488888888889
+    },
+    "ArchaeologicalEnv": {
+        "qwen2.5-3b-instruct": 1.0586,
+        "qwen2.5-7b-instruct": 0.8644000000000001,
+        "qwen2.5-14b-instruct": 0.7687333333333333,
+        "qwen2.5-32b-instruct": 0.724,
+        "qwen2.5-72b-instruct": 0.7683333333333333,
+        "llama-3.1-8b-instruct": 1.0757999999999999,
+        "llama-3.1-70b-instruct": 0.7328666666666667,
+        "llama-3.2-3b-instruct": 1.0688666666666666,
+        "llama-3.3-70b-instruct": 0.7887333333333334,
+        "mistral-large-instruct-2411": 0.7232,
+        "gemma-2-27b-it": 0.8009999999999999,
+        "gemma-2-9b-it": 1.0729333333333333,
+        "deepseek-v3": 0.6970000000000001,
+        "deepseek-r1": 0.5904666666666667,
+        "qwq-32b": 0.6000666666666665,
+        "Average": 0.8223333333333332
+    },
+    "GemstoneEnv": {
+        "qwen2.5-3b-instruct": 0.7110285714285715,
+        "qwen2.5-7b-instruct": 0.7523809523809524,
+        "qwen2.5-14b-instruct": 0.4729333333333333,
+        "qwen2.5-32b-instruct": 0.5357714285714286,
+        "qwen2.5-72b-instruct": 0.6073238095238096,
+        "llama-3.1-8b-instruct": 0.8096666666666665,
+        "llama-3.1-70b-instruct": 0.6153904761904763,
+        "llama-3.2-3b-instruct": 0.7933904761904762,
+        "llama-3.3-70b-instruct": 0.5937238095238094,
+        "mistral-large-instruct-2411": 0.4208952380952381,
+        "gemma-2-27b-it": 0.5776761904761905,
+        "gemma-2-9b-it": 0.7067619047619047,
+        "deepseek-v3": 0.41441904761904763,
+        "deepseek-r1": 0.38596190476190473,
+        "qwq-32b": 0.34542857142857136,
+        "Average": 0.5828501587301588
+    },
+    "MicrobiologyEnv": {
+        "qwen2.5-3b-instruct": 0.9303809523809525,
+        "qwen2.5-7b-instruct": 0.9467904761904762,
+        "qwen2.5-14b-instruct": 0.5958380952380952,
+        "qwen2.5-32b-instruct": 0.6932190476190476,
+        "qwen2.5-72b-instruct": 0.5158190476190476,
+        "llama-3.1-8b-instruct": 0.9718666666666668,
+        "llama-3.1-70b-instruct": 0.7010476190476191,
+        "llama-3.2-3b-instruct": 1.0090190476190477,
+        "llama-3.3-70b-instruct": 0.7338666666666666,
+        "mistral-large-instruct-2411": 0.6196380952380951,
+        "gemma-2-27b-it": 0.7761333333333335,
+        "gemma-2-9b-it": 1.0257809523809525,
+        "deepseek-v3": 0.5738761904761904,
+        "deepseek-r1": 0.5433809523809524,
+        "qwq-32b": 0.5820380952380952,
+        "Average": 0.7479130158730157
+    },
+    "SciFiEnv": {
+        "qwen2.5-3b-instruct": 0.9241999999999999,
+        "qwen2.5-7b-instruct": 1.222,
+        "qwen2.5-14b-instruct": 0.6346,
+        "qwen2.5-32b-instruct": 0.6923333333333332,
+        "qwen2.5-72b-instruct": 0.7514666666666667,
+        "llama-3.1-8b-instruct": 1.1545999999999998,
+        "llama-3.1-70b-instruct": 0.6702,
+        "llama-3.2-3b-instruct": 1.0696,
+        "llama-3.3-70b-instruct": 0.7630666666666667,
+        "mistral-large-instruct-2411": 0.6732666666666667,
+        "gemma-2-27b-it": 0.8202,
+        "gemma-2-9b-it": 1.0992666666666666,
+        "deepseek-v3": 0.6295999999999999,
+        "deepseek-r1": 0.5723333333333334,
+        "qwq-32b": 0.6310666666666667,
+        "Average": 0.82052
+    },
+    "HormoneEnv": {
+        "qwen2.5-3b-instruct": 0.6477999999999999,
+        "qwen2.5-7b-instruct": 0.5792666666666666,
+        "qwen2.5-14b-instruct": 0.42300000000000004,
+        "qwen2.5-32b-instruct": 0.4808,
+        "qwen2.5-72b-instruct": 0.47140000000000004,
+        "llama-3.1-8b-instruct": 0.6914,
+        "llama-3.1-70b-instruct": 0.3943333333333333,
+        "llama-3.2-3b-instruct": 0.6731999999999999,
+        "llama-3.3-70b-instruct": 0.4046,
+        "mistral-large-instruct-2411": 0.47793333333333327,
+        "gemma-2-27b-it": 0.49526666666666663,
+        "gemma-2-9b-it": 0.6825333333333333,
+        "deepseek-v3": 0.4746666666666667,
+        "deepseek-r1": 0.4145333333333333,
+        "qwq-32b": 0.4527333333333333,
+        "Average": 0.5175644444444445
+    },
+    "SculptorEnv": {
+        "qwen2.5-3b-instruct": 1.1031333333333335,
+        "qwen2.5-7b-instruct": 0.9707333333333334,
+        "qwen2.5-14b-instruct": 0.8746666666666666,
+        "qwen2.5-32b-instruct": 0.9588666666666666,
+        "qwen2.5-72b-instruct": 0.9808,
+        "llama-3.1-8b-instruct": 1.215,
+        "llama-3.1-70b-instruct": 1.0109333333333332,
+        "llama-3.2-3b-instruct": 1.2163333333333335,
+        "llama-3.3-70b-instruct": 0.9847999999999999,
+        "mistral-large-instruct-2411": 0.9626666666666667,
+        "gemma-2-27b-it": 1.1294666666666668,
+        "gemma-2-9b-it": 1.2386666666666666,
+        "deepseek-v3": 0.9729333333333333,
+        "deepseek-r1": 0.8991999999999999,
+        "qwq-32b": 0.9352666666666666,
+        "Average": 1.0302311111111113
+    },
+    "NeuroEnv": {
+        "qwen2.5-3b-instruct": 1.0565999999999998,
+        "qwen2.5-7b-instruct": 0.9228666666666665,
+        "qwen2.5-14b-instruct": 0.6512666666666667,
+        "qwen2.5-32b-instruct": 0.7456666666666667,
+        "qwen2.5-72b-instruct": 0.628,
+        "llama-3.1-8b-instruct": 1.0157333333333336,
+        "llama-3.1-70b-instruct": 0.6142,
+        "llama-3.2-3b-instruct": 1.0081333333333333,
+        "llama-3.3-70b-instruct": 0.5914,
+        "mistral-large-instruct-2411": 0.7068,
+        "gemma-2-27b-it": 0.6496666666666667,
+        "gemma-2-9b-it": 1.0555333333333334,
+        "deepseek-v3": 0.7531333333333333,
+        "deepseek-r1": 0.6508666666666667,
+        "qwq-32b": 0.8050666666666666,
+        "Average": 0.7903288888888889
+    },
+    "OceanEnv": {
+        "qwen2.5-3b-instruct": 0.9513333333333334,
+        "qwen2.5-7b-instruct": 0.766,
+        "qwen2.5-14b-instruct": 0.6742,
+        "qwen2.5-32b-instruct": 0.7434,
+        "qwen2.5-72b-instruct": 0.6952666666666667,
+        "llama-3.1-8b-instruct": 0.9298666666666667,
+        "llama-3.1-70b-instruct": 0.6888,
+        "llama-3.2-3b-instruct": 1.0092666666666668,
+        "llama-3.3-70b-instruct": 0.7631333333333334,
+        "mistral-large-instruct-2411": 0.6806000000000001,
+        "gemma-2-27b-it": 0.8006666666666667,
+        "gemma-2-9b-it": 0.9381333333333334,
+        "deepseek-v3": 0.5634666666666666,
+        "deepseek-r1": 0.5218666666666666,
+        "qwq-32b": 0.5317333333333332,
+        "Average": 0.7505155555555555
+    },
+    "MineralEnv": {
+        "qwen2.5-3b-instruct": 0.4416333333333333,
+        "qwen2.5-7b-instruct": 0.40716190476190484,
+        "qwen2.5-14b-instruct": 0.13431428571428572,
+        "qwen2.5-32b-instruct": 0.18465714285714285,
+        "qwen2.5-72b-instruct": 0.17393809523809525,
+        "llama-3.1-8b-instruct": 0.4482333333333333,
+        "llama-3.1-70b-instruct": 0.2729857142857143,
+        "llama-3.2-3b-instruct": 0.46588571428571424,
+        "llama-3.3-70b-instruct": 0.2577333333333333,
+        "mistral-large-instruct-2411": 0.2553095238095238,
+        "gemma-2-27b-it": 0.3398333333333333,
+        "gemma-2-9b-it": 0.4829333333333333,
+        "deepseek-v3": 0.17311428571428572,
+        "deepseek-r1": 0.19182857142857146,
+        "qwq-32b": 0.2801666666666667,
+        "Average": 0.30064857142857143
+    },
+    "FishEnv": {
+        "qwen2.5-3b-instruct": 1.2468666666666668,
+        "qwen2.5-7b-instruct": 1.3481999999999998,
+        "qwen2.5-14b-instruct": 0.9705999999999999,
+        "qwen2.5-32b-instruct": 1.0598666666666667,
+        "qwen2.5-72b-instruct": 0.9867999999999999,
+        "llama-3.1-8b-instruct": 1.3636666666666666,
+        "llama-3.1-70b-instruct": 1.0207333333333335,
+        "llama-3.2-3b-instruct": 1.4142666666666668,
+        "llama-3.3-70b-instruct": 1.0358,
+        "mistral-large-instruct-2411": 0.9927999999999999,
+        "gemma-2-27b-it": 1.1742,
+        "gemma-2-9b-it": 1.3645999999999998,
+        "deepseek-v3": 1.0188,
+        "deepseek-r1": 0.9213333333333333,
+        "qwq-32b": 0.9852666666666667,
+        "Average": 1.12692
+    },
+    "MartialArtsEnv": {
+        "qwen2.5-3b-instruct": 1.0723333333333334,
+        "qwen2.5-7b-instruct": 1.0198,
+        "qwen2.5-14b-instruct": 0.7902666666666667,
+        "qwen2.5-32b-instruct": 0.8842000000000001,
+        "qwen2.5-72b-instruct": 0.9042666666666666,
+        "llama-3.1-8b-instruct": 1.117,
+        "llama-3.1-70b-instruct": 0.8526666666666667,
+        "llama-3.2-3b-instruct": 1.1304,
+        "llama-3.3-70b-instruct": 0.9208000000000001,
+        "mistral-large-instruct-2411": 0.8798666666666666,
+        "gemma-2-27b-it": 1.0068666666666666,
+        "gemma-2-9b-it": 1.1265333333333334,
+        "deepseek-v3": 0.7828666666666667,
+        "deepseek-r1": 0.7744,
+        "qwq-32b": 0.8414000000000001,
+        "Average": 0.9402444444444444
+    },
+    "RocketFuelEnv": {
+        "qwen2.5-3b-instruct": 0.8296666666666667,
+        "qwen2.5-7b-instruct": 0.8119333333333334,
+        "qwen2.5-14b-instruct": 0.3957333333333334,
+        "qwen2.5-32b-instruct": 0.5435333333333333,
+        "qwen2.5-72b-instruct": 0.4489333333333333,
+        "llama-3.1-8b-instruct": 0.8727333333333332,
+        "llama-3.1-70b-instruct": 0.5453999999999999,
+        "llama-3.2-3b-instruct": 0.8820666666666666,
+        "llama-3.3-70b-instruct": 0.5007333333333334,
+        "mistral-large-instruct-2411": 0.4926666666666666,
+        "gemma-2-27b-it": 0.5702666666666667,
+        "gemma-2-9b-it": 0.9189333333333332,
+        "deepseek-v3": 0.45919999999999994,
+        "deepseek-r1": 0.44160000000000005,
+        "qwq-32b": 0.4107333333333333,
+        "Average": 0.6082755555555556
+    },
+    "MLEnv": {
+        "qwen2.5-3b-instruct": 1.0853809523809523,
+        "qwen2.5-7b-instruct": 0.9570571428571428,
+        "qwen2.5-14b-instruct": 0.7381333333333332,
+        "qwen2.5-32b-instruct": 0.7021238095238095,
+        "qwen2.5-72b-instruct": 0.6462666666666667,
+        "llama-3.1-8b-instruct": 1.0434,
+        "llama-3.1-70b-instruct": 0.6853333333333332,
+        "llama-3.2-3b-instruct": 1.0912,
+        "llama-3.3-70b-instruct": 0.8062666666666667,
+        "mistral-large-instruct-2411": 0.742590476190476,
+        "gemma-2-27b-it": 0.9825333333333333,
+        "gemma-2-9b-it": 1.1573333333333333,
+        "deepseek-v3": 0.7192761904761905,
+        "deepseek-r1": 0.6918,
+        "qwq-32b": 0.6837333333333333,
+        "Average": 0.8488285714285714
+    },
+    "PoliticalManifestoEnv": {
+        "qwen2.5-3b-instruct": 1.094,
+        "qwen2.5-7b-instruct": 1.0524666666666664,
+        "qwen2.5-14b-instruct": 0.8964666666666666,
+        "qwen2.5-32b-instruct": 0.9097333333333332,
+        "qwen2.5-72b-instruct": 0.9074666666666668,
+        "llama-3.1-8b-instruct": 1.1484666666666665,
+        "llama-3.1-70b-instruct": 0.9022666666666666,
+        "llama-3.2-3b-instruct": 1.2590666666666668,
+        "llama-3.3-70b-instruct": 0.9182666666666666,
+        "mistral-large-instruct-2411": 0.9239333333333335,
+        "gemma-2-27b-it": 1.1248666666666667,
+        "gemma-2-9b-it": 1.2280666666666664,
+        "deepseek-v3": 0.9872,
+        "deepseek-r1": 0.9032,
+        "qwq-32b": 0.9002666666666667,
+        "Average": 1.0103822222222223
+    },
+    "CoffeeEnv": {
+        "qwen2.5-3b-instruct": 0.5574857142857143,
+        "qwen2.5-7b-instruct": 0.5191999999999999,
+        "qwen2.5-14b-instruct": 0.287847619047619,
+        "qwen2.5-32b-instruct": 0.3643714285714286,
+        "qwen2.5-72b-instruct": 0.32374285714285717,
+        "llama-3.1-8b-instruct": 0.6735904761904761,
+        "llama-3.1-70b-instruct": 0.4418666666666667,
+        "llama-3.2-3b-instruct": 0.6586857142857143,
+        "llama-3.3-70b-instruct": 0.3596190476190476,
+        "mistral-large-instruct-2411": 0.32551428571428564,
+        "gemma-2-27b-it": 0.4073619047619047,
+        "gemma-2-9b-it": 0.5588,
+        "deepseek-v3": 0.3131333333333334,
+        "deepseek-r1": 0.2641047619047619,
+        "qwq-32b": 0.2930095238095238,
+        "Average": 0.4232222222222221
+    },
+    "MotifAnalysisEnv": {
+        "qwen2.5-3b-instruct": 1.5359333333333334,
+        "qwen2.5-7b-instruct": 1.3934000000000002,
+        "qwen2.5-14b-instruct": 1.2638,
+        "qwen2.5-32b-instruct": 1.3157999999999999,
+        "qwen2.5-72b-instruct": 1.2424,
+        "llama-3.1-8b-instruct": 1.5532666666666666,
+        "llama-3.1-70b-instruct": 1.3790666666666664,
+        "llama-3.2-3b-instruct": 1.6122,
+        "llama-3.3-70b-instruct": 1.5049333333333332,
+        "mistral-large-instruct-2411": 1.2954666666666665,
+        "gemma-2-27b-it": 1.5349999999999997,
+        "gemma-2-9b-it": 1.5813333333333335,
+        "deepseek-v3": 1.1815333333333333,
+        "deepseek-r1": 0.9527999999999999,
+        "qwq-32b": 1.0904666666666667,
+        "Average": 1.3624933333333333
+    },
+    "NutritionEnv": {
+        "qwen2.5-3b-instruct": 1.1223333333333332,
+        "qwen2.5-7b-instruct": 1.1436666666666666,
+        "qwen2.5-14b-instruct": 0.8542666666666667,
+        "qwen2.5-32b-instruct": 0.8586666666666666,
+        "qwen2.5-72b-instruct": 0.8068666666666667,
+        "llama-3.1-8b-instruct": 1.1504666666666665,
+        "llama-3.1-70b-instruct": 0.7640666666666667,
+        "llama-3.2-3b-instruct": 1.1206666666666667,
+        "llama-3.3-70b-instruct": 0.7728,
+        "mistral-large-instruct-2411": 0.8578666666666667,
+        "gemma-2-27b-it": 0.9822,
+        "gemma-2-9b-it": 1.1840000000000002,
+        "deepseek-v3": 0.8118666666666666,
+        "deepseek-r1": 0.8373333333333333,
+        "qwq-32b": 0.8091999999999999,
+        "Average": 0.9384177777777779
+    },
+    "MalwareEnv": {
+        "qwen2.5-3b-instruct": 1.0660666666666665,
+        "qwen2.5-7b-instruct": 0.9987333333333333,
+        "qwen2.5-14b-instruct": 0.8055999999999999,
+        "qwen2.5-32b-instruct": 0.9301333333333333,
+        "qwen2.5-72b-instruct": 0.8351333333333333,
+        "llama-3.1-8b-instruct": 1.0980666666666667,
+        "llama-3.1-70b-instruct": 0.8638666666666666,
+        "llama-3.2-3b-instruct": 1.1550666666666667,
+        "llama-3.3-70b-instruct": 0.9002666666666667,
+        "mistral-large-instruct-2411": 0.8474,
+        "gemma-2-27b-it": 1.0784666666666667,
+        "gemma-2-9b-it": 1.1739333333333335,
+        "deepseek-v3": 0.8863333333333333,
+        "deepseek-r1": 0.7370666666666666,
+        "qwq-32b": 0.8452666666666666,
+        "Average": 0.9480933333333336
+    },
+    "GeologicalEnv": {
+        "qwen2.5-3b-instruct": 0.7544666666666666,
+        "qwen2.5-7b-instruct": 0.6998666666666666,
+        "qwen2.5-14b-instruct": 0.5382,
+        "qwen2.5-32b-instruct": 0.6078666666666667,
+        "qwen2.5-72b-instruct": 0.5856,
+        "llama-3.1-8b-instruct": 0.8460666666666666,
+        "llama-3.1-70b-instruct": 0.6026,
+        "llama-3.2-3b-instruct": 0.7952666666666668,
+        "llama-3.3-70b-instruct": 0.6526,
+        "mistral-large-instruct-2411": 0.5856666666666667,
+        "gemma-2-27b-it": 0.7190666666666667,
+        "gemma-2-9b-it": 0.8308666666666668,
+        "deepseek-v3": 0.5351333333333332,
+        "deepseek-r1": 0.5818,
+        "qwq-32b": 0.5489999999999999,
+        "Average": 0.6589377777777776
+    },
+    "TheatricalEnv": {
+        "qwen2.5-3b-instruct": 1.0014666666666667,
+        "qwen2.5-7b-instruct": 0.9438000000000001,
+        "qwen2.5-14b-instruct": 0.7684666666666666,
+        "qwen2.5-32b-instruct": 0.7975333333333333,
+        "qwen2.5-72b-instruct": 0.7806666666666666,
+        "llama-3.1-8b-instruct": 0.9822666666666666,
+        "llama-3.1-70b-instruct": 0.6897333333333333,
+        "llama-3.2-3b-instruct": 1.2334666666666667,
+        "llama-3.3-70b-instruct": 0.7385333333333334,
+        "mistral-large-instruct-2411": 0.7150666666666667,
+        "gemma-2-27b-it": 0.9279999999999999,
+        "gemma-2-9b-it": 1.0476666666666667,
+        "deepseek-v3": 0.7080666666666667,
+        "deepseek-r1": 0.7016000000000001,
+        "qwq-32b": 0.7614000000000001,
+        "Average": 0.8531822222222224
+    },
+    "PrintingTechniqueEnv": {
+        "qwen2.5-3b-instruct": 0.5242857142857142,
+        "qwen2.5-7b-instruct": 0.4669809523809524,
+        "qwen2.5-14b-instruct": 0.2997142857142857,
+        "qwen2.5-32b-instruct": 0.3549714285714286,
+        "qwen2.5-72b-instruct": 0.27769523809523805,
+        "llama-3.1-8b-instruct": 0.5112857142857143,
+        "llama-3.1-70b-instruct": 0.3614476190476191,
+        "llama-3.2-3b-instruct": 0.5472571428571429,
+        "llama-3.3-70b-instruct": 0.3488571428571428,
+        "mistral-large-instruct-2411": 0.34679999999999994,
+        "gemma-2-27b-it": 0.4303714285714285,
+        "gemma-2-9b-it": 0.5662952380952382,
+        "deepseek-v3": 0.29273333333333335,
+        "deepseek-r1": 0.31156190476190476,
+        "qwq-32b": 0.3049809523809524,
+        "Average": 0.3963492063492063
+    },
+    "StellarEnv": {
+        "qwen2.5-3b-instruct": 0.9369333333333332,
+        "qwen2.5-7b-instruct": 0.7797999999999999,
+        "qwen2.5-14b-instruct": 0.6935333333333333,
+        "qwen2.5-32b-instruct": 0.7302666666666666,
+        "qwen2.5-72b-instruct": 0.6992,
+        "llama-3.1-8b-instruct": 0.9464666666666665,
+        "llama-3.1-70b-instruct": 0.7085999999999999,
+        "llama-3.2-3b-instruct": 0.9724666666666666,
+        "llama-3.3-70b-instruct": 0.7429999999999999,
+        "mistral-large-instruct-2411": 0.6746,
+        "gemma-2-27b-it": 0.8274666666666667,
+        "gemma-2-9b-it": 0.9978,
+        "deepseek-v3": 0.6367333333333333,
+        "deepseek-r1": 0.6487333333333332,
+        "qwq-32b": 0.7190666666666667,
+        "Average": 0.7809777777777777
+    },
+    "SoilEnv": {
+        "qwen2.5-3b-instruct": 1.2182666666666666,
+        "qwen2.5-7b-instruct": 1.0028666666666668,
+        "qwen2.5-14b-instruct": 0.8012666666666665,
+        "qwen2.5-32b-instruct": 0.8625999999999999,
+        "qwen2.5-72b-instruct": 0.7968666666666666,
+        "llama-3.1-8b-instruct": 1.1898,
+        "llama-3.1-70b-instruct": 0.8916000000000001,
+        "llama-3.2-3b-instruct": 1.1725333333333334,
+        "llama-3.3-70b-instruct": 0.9216,
+        "mistral-large-instruct-2411": 0.8744,
+        "gemma-2-27b-it": 0.9574666666666667,
+        "gemma-2-9b-it": 1.1284,
+        "deepseek-v3": 0.9315333333333333,
+        "deepseek-r1": 0.8695333333333334,
+        "qwq-32b": 0.8491333333333333,
+        "Average": 0.9645244444444445
+    },
+    "SoftwareEnv": {
+        "qwen2.5-3b-instruct": 0.7055999999999999,
+        "qwen2.5-7b-instruct": 0.6421333333333334,
+        "qwen2.5-14b-instruct": 0.4560666666666666,
+        "qwen2.5-32b-instruct": 0.484,
+        "qwen2.5-72b-instruct": 0.4653999999999999,
+        "llama-3.1-8b-instruct": 0.6588666666666667,
+        "llama-3.1-70b-instruct": 0.4653333333333333,
+        "llama-3.2-3b-instruct": 0.7011999999999998,
+        "llama-3.3-70b-instruct": 0.49446666666666667,
+        "mistral-large-instruct-2411": 0.46806666666666663,
+        "gemma-2-27b-it": 0.6290000000000001,
+        "gemma-2-9b-it": 0.7563333333333333,
+        "deepseek-v3": 0.46806666666666674,
+        "deepseek-r1": 0.4063333333333333,
+        "qwq-32b": 0.4793333333333333,
+        "Average": 0.5520133333333334
+    },
+    "CarIdentificationEnv": {
+        "qwen2.5-3b-instruct": 0.6415809523809524,
+        "qwen2.5-7b-instruct": 0.7830761904761905,
+        "qwen2.5-14b-instruct": 0.11047619047619046,
+        "qwen2.5-32b-instruct": 0.1649142857142857,
+        "qwen2.5-72b-instruct": 0.11052380952380951,
+        "llama-3.1-8b-instruct": 0.6149333333333332,
+        "llama-3.1-70b-instruct": 0.30315238095238095,
+        "llama-3.2-3b-instruct": 0.8439333333333332,
+        "llama-3.3-70b-instruct": 0.23700952380952378,
+        "mistral-large-instruct-2411": 0.2485809523809524,
+        "gemma-2-27b-it": 0.3316761904761905,
+        "gemma-2-9b-it": 0.6974666666666666,
+        "deepseek-v3": 0.18107619047619045,
+        "deepseek-r1": 0.21692380952380952,
+        "qwq-32b": 0.25435238095238094,
+        "Average": 0.38264507936507924
+    },
+    "PharmaceuticalEnv": {
+        "qwen2.5-3b-instruct": 0.6446285714285713,
+        "qwen2.5-7b-instruct": 0.6438761904761904,
+        "qwen2.5-14b-instruct": 0.46221904761904764,
+        "qwen2.5-32b-instruct": 0.5071333333333333,
+        "qwen2.5-72b-instruct": 0.47396190476190475,
+        "llama-3.1-8b-instruct": 0.7244190476190476,
+        "llama-3.1-70b-instruct": 0.5232666666666667,
+        "llama-3.2-3b-instruct": 0.7074666666666667,
+        "llama-3.3-70b-instruct": 0.5709238095238094,
+        "mistral-large-instruct-2411": 0.5165238095238095,
+        "gemma-2-27b-it": 0.639904761904762,
+        "gemma-2-9b-it": 0.7634666666666667,
+        "deepseek-v3": 0.5126,
+        "deepseek-r1": 0.5030857142857144,
+        "qwq-32b": 0.5336571428571428,
+        "Average": 0.5818088888888888
+    },
+    "NetworkEnv": {
+        "qwen2.5-3b-instruct": 0.9304666666666666,
+        "qwen2.5-7b-instruct": 0.9181333333333332,
+        "qwen2.5-14b-instruct": 0.7156,
+        "qwen2.5-32b-instruct": 0.7281333333333334,
+        "qwen2.5-72b-instruct": 0.7013333333333333,
+        "llama-3.1-8b-instruct": 0.9331333333333334,
+        "llama-3.1-70b-instruct": 0.6774666666666667,
+        "llama-3.2-3b-instruct": 1.0052666666666665,
+        "llama-3.3-70b-instruct": 0.6723999999999999,
+        "mistral-large-instruct-2411": 0.6792666666666667,
+        "gemma-2-27b-it": 0.8334666666666667,
+        "gemma-2-9b-it": 0.9756,
+        "deepseek-v3": 0.6752666666666667,
+        "deepseek-r1": 0.6507333333333334,
+        "qwq-32b": 0.7018000000000001,
+        "Average": 0.7865377777777778
+    },
+    "BirdNestEnv": {
+        "qwen2.5-3b-instruct": 0.9391333333333332,
+        "qwen2.5-7b-instruct": 0.9543333333333333,
+        "qwen2.5-14b-instruct": 0.8100666666666665,
+        "qwen2.5-32b-instruct": 0.9158,
+        "qwen2.5-72b-instruct": 0.8606666666666666,
+        "llama-3.1-8b-instruct": 0.9903999999999998,
+        "llama-3.1-70b-instruct": 0.9222666666666666,
+        "llama-3.2-3b-instruct": 1.026333333333333,
+        "llama-3.3-70b-instruct": 0.9565999999999999,
+        "mistral-large-instruct-2411": 0.8474666666666666,
+        "gemma-2-27b-it": 0.9609333333333334,
+        "gemma-2-9b-it": 1.0085333333333333,
+        "deepseek-v3": 0.7617999999999998,
+        "deepseek-r1": 0.6876,
+        "qwq-32b": 0.7255999999999999,
+        "Average": 0.8911688888888886
+    },
+    "EnergyEnv": {
+        "qwen2.5-3b-instruct": 1.0884,
+        "qwen2.5-7b-instruct": 1.0123904761904763,
+        "qwen2.5-14b-instruct": 0.7312285714285716,
+        "qwen2.5-32b-instruct": 0.8728190476190475,
+        "qwen2.5-72b-instruct": 0.8609333333333332,
+        "llama-3.1-8b-instruct": 1.1586666666666665,
+        "llama-3.1-70b-instruct": 0.9046,
+        "llama-3.2-3b-instruct": 1.1040666666666665,
+        "llama-3.3-70b-instruct": 1.0045904761904763,
+        "mistral-large-instruct-2411": 0.7872380952380952,
+        "gemma-2-27b-it": 1.0375904761904762,
+        "gemma-2-9b-it": 1.1858666666666666,
+        "deepseek-v3": 0.8143523809523809,
+        "deepseek-r1": 0.6982476190476191,
+        "qwq-32b": 0.7441428571428571,
+        "Average": 0.9336755555555555
+    },
+    "LanguageEnv": {
+        "qwen2.5-3b-instruct": 1.1255333333333333,
+        "qwen2.5-7b-instruct": 1.1768,
+        "qwen2.5-14b-instruct": 1.0519333333333332,
+        "qwen2.5-32b-instruct": 0.9997999999999999,
+        "qwen2.5-72b-instruct": 0.9798000000000002,
+        "llama-3.1-8b-instruct": 1.1883333333333335,
+        "llama-3.1-70b-instruct": 1.0505333333333333,
+        "llama-3.2-3b-instruct": 1.204333333333333,
+        "llama-3.3-70b-instruct": 1.1250666666666667,
+        "mistral-large-instruct-2411": 0.9846666666666666,
+        "gemma-2-27b-it": 1.1916666666666669,
+        "gemma-2-9b-it": 1.2723333333333335,
+        "deepseek-v3": 0.9475333333333333,
+        "deepseek-r1": 0.7798666666666666,
+        "qwq-32b": 0.8547333333333332,
+        "Average": 1.0621955555555558
+    },
+    "AlgorithmEnv": {
+        "qwen2.5-3b-instruct": 0.9703333333333333,
+        "qwen2.5-7b-instruct": 0.8614666666666666,
+        "qwen2.5-14b-instruct": 0.6675333333333334,
+        "qwen2.5-32b-instruct": 0.7172,
+        "qwen2.5-72b-instruct": 0.7046666666666666,
+        "llama-3.1-8b-instruct": 0.8993333333333332,
+        "llama-3.1-70b-instruct": 0.6912666666666667,
+        "llama-3.2-3b-instruct": 0.8341333333333333,
+        "llama-3.3-70b-instruct": 0.7737333333333333,
+        "mistral-large-instruct-2411": 0.6648000000000001,
+        "gemma-2-27b-it": 0.9326000000000001,
+        "gemma-2-9b-it": 1.0570666666666668,
+        "deepseek-v3": 0.7781333333333332,
+        "deepseek-r1": 0.6048,
+        "qwq-32b": 0.656,
+        "Average": 0.787537777777778
+    },
+    "MathematicalEnv": {
+        "qwen2.5-3b-instruct": 0.7803333333333333,
+        "qwen2.5-7b-instruct": 0.5459333333333333,
+        "qwen2.5-14b-instruct": 0.4785333333333333,
+        "qwen2.5-32b-instruct": 0.5025333333333333,
+        "qwen2.5-72b-instruct": 0.47973333333333334,
+        "llama-3.1-8b-instruct": 0.7568666666666667,
+        "llama-3.1-70b-instruct": 0.4238666666666667,
+        "llama-3.2-3b-instruct": 0.7148666666666668,
+        "llama-3.3-70b-instruct": 0.4582,
+        "mistral-large-instruct-2411": 0.4603999999999999,
+        "gemma-2-27b-it": 0.6693333333333333,
+        "gemma-2-9b-it": 0.8029999999999999,
+        "deepseek-v3": 0.44066666666666665,
+        "deepseek-r1": 0.3256,
+        "qwq-32b": 0.41286666666666666,
+        "Average": 0.5501822222222222
+    },
+    "MusicalEnv": {
+        "qwen2.5-3b-instruct": 0.7868666666666665,
+        "qwen2.5-7b-instruct": 0.6212,
+        "qwen2.5-14b-instruct": 0.4023333333333333,
+        "qwen2.5-32b-instruct": 0.44286666666666663,
+        "qwen2.5-72b-instruct": 0.40346666666666664,
+        "llama-3.1-8b-instruct": 0.6890666666666666,
+        "llama-3.1-70b-instruct": 0.43373333333333336,
+        "llama-3.2-3b-instruct": 0.7595333333333332,
+        "llama-3.3-70b-instruct": 0.3923333333333333,
+        "mistral-large-instruct-2411": 0.46593333333333337,
+        "gemma-2-27b-it": 0.6487999999999999,
+        "gemma-2-9b-it": 0.7524,
+        "deepseek-v3": 0.47313333333333335,
+        "deepseek-r1": 0.4392666666666667,
+        "qwq-32b": 0.4437333333333334,
+        "Average": 0.5436444444444444
+    },
+    "InventorEnv": {
+        "qwen2.5-3b-instruct": 1.1748,
+        "qwen2.5-7b-instruct": 1.0563999999999998,
+        "qwen2.5-14b-instruct": 0.7145333333333334,
+        "qwen2.5-32b-instruct": 0.7015999999999999,
+        "qwen2.5-72b-instruct": 0.7992666666666667,
+        "llama-3.1-8b-instruct": 1.1523999999999996,
+        "llama-3.1-70b-instruct": 0.7999333333333334,
+        "llama-3.2-3b-instruct": 1.2088,
+        "llama-3.3-70b-instruct": 0.9067333333333334,
+        "mistral-large-instruct-2411": 0.6736000000000001,
+        "gemma-2-27b-it": 0.8846,
+        "gemma-2-9b-it": 1.2016666666666667,
+        "deepseek-v3": 0.5913333333333333,
+        "deepseek-r1": 0.5467333333333333,
+        "qwq-32b": 0.5757333333333332,
+        "Average": 0.8658755555555557
+    },
+    "MedicalEnv": {
+        "qwen2.5-3b-instruct": 0.6536,
+        "qwen2.5-7b-instruct": 0.5706761904761904,
+        "qwen2.5-14b-instruct": 0.49113333333333326,
+        "qwen2.5-32b-instruct": 0.5525238095238094,
+        "qwen2.5-72b-instruct": 0.4351047619047619,
+        "llama-3.1-8b-instruct": 0.675742857142857,
+        "llama-3.1-70b-instruct": 0.4085142857142857,
+        "llama-3.2-3b-instruct": 0.6928952380952381,
+        "llama-3.3-70b-instruct": 0.44421904761904757,
+        "mistral-large-instruct-2411": 0.3882190476190476,
+        "gemma-2-27b-it": 0.4850761904761905,
+        "gemma-2-9b-it": 0.6444000000000001,
+        "deepseek-v3": 0.42532380952380955,
+        "deepseek-r1": 0.4207714285714285,
+        "qwq-32b": 0.5122666666666668,
+        "Average": 0.5200311111111111
+    },
+    "MusicEnv": {
+        "qwen2.5-3b-instruct": 0.8416666666666666,
+        "qwen2.5-7b-instruct": 1.0005333333333333,
+        "qwen2.5-14b-instruct": 0.6241333333333333,
+        "qwen2.5-32b-instruct": 0.6859999999999999,
+        "qwen2.5-72b-instruct": 0.5986190476190476,
+        "llama-3.1-8b-instruct": 0.8823619047619047,
+        "llama-3.1-70b-instruct": 0.620095238095238,
+        "llama-3.2-3b-instruct": 1.0788857142857142,
+        "llama-3.3-70b-instruct": 0.6707809523809523,
+        "mistral-large-instruct-2411": 0.6624857142857142,
+        "gemma-2-27b-it": 0.7730666666666666,
+        "gemma-2-9b-it": 0.9248000000000001,
+        "deepseek-v3": 0.6254857142857142,
+        "deepseek-r1": 0.6092095238095239,
+        "qwq-32b": 0.6053809523809524,
+        "Average": 0.7469003174603175
+    },
+    "FantasyEnv": {
+        "qwen2.5-3b-instruct": 0.6738,
+        "qwen2.5-7b-instruct": 0.6780571428571429,
+        "qwen2.5-14b-instruct": 0.20936190476190478,
+        "qwen2.5-32b-instruct": 0.23541904761904764,
+        "qwen2.5-72b-instruct": 0.3943904761904762,
+        "llama-3.1-8b-instruct": 0.6281142857142856,
+        "llama-3.1-70b-instruct": 0.3229714285714286,
+        "llama-3.2-3b-instruct": 0.7130571428571428,
+        "llama-3.3-70b-instruct": 0.2710190476190476,
+        "mistral-large-instruct-2411": 0.1259142857142857,
+        "gemma-2-27b-it": 0.35649523809523803,
+        "gemma-2-9b-it": 0.7076952380952382,
+        "deepseek-v3": 0.056790476190476204,
+        "deepseek-r1": -0.025180952380952377,
+        "qwq-32b": 0.03801904761904761,
+        "Average": 0.35906158730158727
+    },
+    "EducationEnv": {
+        "qwen2.5-3b-instruct": 0.9363999999999999,
+        "qwen2.5-7b-instruct": 0.9230666666666666,
+        "qwen2.5-14b-instruct": 0.7015333333333333,
+        "qwen2.5-32b-instruct": 0.6477333333333334,
+        "qwen2.5-72b-instruct": 0.6232,
+        "llama-3.1-8b-instruct": 0.9055333333333333,
+        "llama-3.1-70b-instruct": 0.5771333333333334,
+        "llama-3.2-3b-instruct": 0.8691333333333334,
+        "llama-3.3-70b-instruct": 0.6331333333333333,
+        "mistral-large-instruct-2411": 0.6769333333333332,
+        "gemma-2-27b-it": 0.7234,
+        "gemma-2-9b-it": 0.8838666666666667,
+        "deepseek-v3": 0.7129333333333334,
+        "deepseek-r1": 0.7282666666666666,
+        "qwq-32b": 0.7233333333333334,
+        "Average": 0.7510399999999999
+    },
+    "ChemicalEnv": {
+        "qwen2.5-3b-instruct": 1.0222666666666664,
+        "qwen2.5-7b-instruct": 1.1687333333333334,
+        "qwen2.5-14b-instruct": 0.8354666666666667,
+        "qwen2.5-32b-instruct": 0.8561333333333334,
+        "qwen2.5-72b-instruct": 0.8254666666666667,
+        "llama-3.1-8b-instruct": 1.1288,
+        "llama-3.1-70b-instruct": 0.8285333333333333,
+        "llama-3.2-3b-instruct": 1.1526666666666665,
+        "llama-3.3-70b-instruct": 0.9390666666666666,
+        "mistral-large-instruct-2411": 0.8290666666666666,
+        "gemma-2-27b-it": 0.953533333333333,
+        "gemma-2-9b-it": 1.1003333333333334,
+        "deepseek-v3": 0.8336666666666668,
+        "deepseek-r1": 0.8385333333333334,
+        "qwq-32b": 0.7902666666666667,
+        "Average": 0.9401688888888889
+    },
+    "Average": {
+        "qwen2.5-3b-instruct": 0.9038483262611976,
+        "qwen2.5-7b-instruct": 0.867841584158416,
+        "qwen2.5-14b-instruct": 0.635130598774163,
+        "qwen2.5-32b-instruct": 0.6698686468646864,
+        "qwen2.5-72b-instruct": 0.6424673738802452,
+        "llama-3.1-8b-instruct": 0.9346749174917492,
+        "llama-3.1-70b-instruct": 0.660992975011787,
+        "llama-3.2-3b-instruct": 0.9649007072135783,
+        "llama-3.3-70b-instruct": 0.6869286185761432,
+        "mistral-large-instruct-2411": 0.6406110796793965,
+        "gemma-2-27b-it": 0.7896256954266856,
+        "gemma-2-9b-it": 0.9722245167373881,
+        "deepseek-v3": 0.6361851013672796,
+        "deepseek-r1": 0.5821313531353135,
+        "qwq-32b": 0.6111832626119755
+    }
+}

data/easy_0402.json

@@ -0,0 +1,97 @@
+      
+{
+    "llama-3.2-3b-instruct": {
+        "success_rate": 0.18239999999999998,
+        "relative_action_count": 0.8956800000000001
+    },
+    "qwen2.5-3b-instruct": {
+        "success_rate": 0.184,
+        "relative_action_count": 0.8255466666666665
+    },
+    "gpt-3.5-turbo": {
+        "success_rate": 0.272,
+        "relative_action_count": 0.8743314285714285
+    },
+    "qwen2.5-7b-instruct": {
+        "success_rate": 0.36639999999999995,
+        "relative_action_count": 0.8682133333333335
+    },
+    "gemma-2-9b-it": {
+        "success_rate": 0.392,
+        "relative_action_count": 0.8522190476190475
+    },
+    "llama-3.1-8b-instruct": {
+        "success_rate": 0.4424,
+        "relative_action_count": 0.8441104761904763
+    },
+    "gemma-2-27b-it": {
+        "success_rate": 0.548,
+        "relative_action_count": 0.6583142857142856
+    },
+    "yi-lightning": {
+        "success_rate": 0.6728,
+        "relative_action_count": 0.5962819047619048
+    },
+    "llama-3.1-70b-instruct": {
+        "success_rate": 0.696,
+        "relative_action_count": 0.5514495238095238
+    },
+    "llama-3.3-70b-instruct": {
+        "success_rate": 0.712,
+        "relative_action_count": 0.5916438095238095
+    },
+    "gpt-4o-mini": {
+        "success_rate": 0.7239999999999999,
+        "relative_action_count": 0.5270952380952381
+    },
+    "gemini-1.5-pro": {
+        "success_rate": 0.7256,
+        "relative_action_count": 0.5686514285714285
+    },
+    "claude-3.5-haiku": {
+        "success_rate": 0.7343999999999999,
+        "relative_action_count": 0.757095238095238
+    },
+    "qwen2.5-14b-instruct": {
+        "success_rate": 0.756,
+        "relative_action_count": 0.5723257142857143
+    },
+    "qwen2.5-72b-instruct": {
+        "success_rate": 0.7584,
+        "relative_action_count": 0.5753561904761904
+    },
+    "gpt-4o": {
+        "success_rate": 0.7856000000000002,
+        "relative_action_count": 0.506207619047619
+    },
+    "qwen2.5-32b-instruct": {
+        "success_rate": 0.7879999999999999,
+        "relative_action_count": 0.5955619047619047
+    },
+    "mistral-large-instruct-2411": {
+        "success_rate": 0.7879999999999999,
+        "relative_action_count": 0.5365238095238094
+    },
+    "claude-3.5-sonnet": {
+        "success_rate": 0.8263999999999999,
+        "relative_action_count": 0.46185714285714285
+    },
+    "deepseek-r1": {
+        "success_rate": 0.8712,
+        "relative_action_count": 0.51432
+    },
+    "o1-mini": {
+        "success_rate": 0.8784000000000001,
+        "relative_action_count": 0.46449523809523807
+    },
+    "deepseek-v3": {
+        "success_rate": 0.8928,
+        "relative_action_count": 0.5308400000000001
+    },
+    "qwq-32b": {
+        "success_rate": 0.9032,
+        "relative_action_count": 0.5338533333333333
+    }
+}
+
+    

data/hard_0402.json

@@ -0,0 +1,97 @@
+      
+{
+    "qwen2.5-3b-instruct": {
+        "success_rate": 0.0624,
+        "relative_action_count": 2.4255102697302697
+    },
+    "llama-3.2-3b-instruct": {
+        "success_rate": 0.064,
+        "relative_action_count": 2.4438042524142523
+    },
+    "llama-3.1-8b-instruct": {
+        "success_rate": 0.11599999999999999,
+        "relative_action_count": 2.3321907026307027
+    },
+    "gpt-3.5-turbo": {
+        "success_rate": 0.12079999999999999,
+        "relative_action_count": 2.34957508047508
+    },
+    "gemma-2-9b-it": {
+        "success_rate": 0.132,
+        "relative_action_count": 2.3394684981684977
+    },
+    "qwen2.5-7b-instruct": {
+        "success_rate": 0.1664,
+        "relative_action_count": 2.3259762459762454
+    },
+    "gemma-2-27b-it": {
+        "success_rate": 0.1696,
+        "relative_action_count": 2.28467764013764
+    },
+    "llama-3.1-70b-instruct": {
+        "success_rate": 0.256,
+        "relative_action_count": 1.9653564912864916
+    },
+    "yi-lightning": {
+        "success_rate": 0.30720000000000003,
+        "relative_action_count": 2.031278719058719
+    },
+    "gpt-4o-mini": {
+        "success_rate": 0.31040000000000006,
+        "relative_action_count": 1.9804984304584305
+    },
+    "llama-3.3-70b-instruct": {
+        "success_rate": 0.33840000000000003,
+        "relative_action_count": 1.90917626040626
+    },
+    "claude-3.5-haiku": {
+        "success_rate": 0.3592000000000001,
+        "relative_action_count": 2.0113219180819177
+    },
+    "gemini-1.5-pro": {
+        "success_rate": 0.36879999999999996,
+        "relative_action_count": 1.9371788544788544
+    },
+    "qwen2.5-14b-instruct": {
+        "success_rate": 0.3816,
+        "relative_action_count": 1.9383408547008547
+    },
+    "qwen2.5-72b-instruct": {
+        "success_rate": 0.4008,
+        "relative_action_count": 1.8648658674658674
+    },
+    "mistral-large-instruct-2411": {
+        "success_rate": 0.4144,
+        "relative_action_count": 1.795764299034299
+    },
+    "qwen2.5-32b-instruct": {
+        "success_rate": 0.43920000000000003,
+        "relative_action_count": 1.8831460717060717
+    },
+    "claude-3.5-sonnet": {
+        "success_rate": 0.44000000000000006,
+        "relative_action_count": 1.6636790032190032
+    },
+    "gpt-4o": {
+        "success_rate": 0.44960000000000006,
+        "relative_action_count": 1.7164597657897656
+    },
+    "deepseek-v3": {
+        "success_rate": 0.5496000000000001,
+        "relative_action_count": 1.705338828948829
+    },
+    "deepseek-r1": {
+        "success_rate": 0.6112,
+        "relative_action_count": 1.4205231568431569
+    },
+    "qwq-32b": {
+        "success_rate": 0.6112,
+        "relative_action_count": 1.5151790675990677
+    },
+    "o1-mini": {
+        "success_rate": 0.6296,
+        "relative_action_count": 1.4230264535464534
+    }
+}
+
+    

data/success_rate_0402.json

@@ -0,0 +1,1819 @@
+{
+    "RelicEnv": {
+        "qwen2.5-3b-instruct": 0.18,
+        "qwen2.5-7b-instruct": 0.396,
+        "qwen2.5-14b-instruct": 0.8,
+        "qwen2.5-32b-instruct": 0.8560000000000001,
+        "qwen2.5-72b-instruct": 0.892,
+        "llama-3.1-8b-instruct": 0.21600000000000003,
+        "llama-3.1-70b-instruct": 0.6639999999999999,
+        "llama-3.2-3b-instruct": 0.164,
+        "llama-3.3-70b-instruct": 0.836,
+        "mistral-large-instruct-2411": 0.8560000000000001,
+        "gemma-2-27b-it": 0.544,
+        "gemma-2-9b-it": 0.36400000000000005,
+        "deepseek-v3": 0.9359999999999999,
+        "deepseek-r1": 0.916,
+        "qwq-32b": 0.9560000000000001,
+        "Average": 0.6384
+    },
+    "HerbEnv": {
+        "qwen2.5-3b-instruct": 0.184,
+        "qwen2.5-7b-instruct": 0.304,
+        "qwen2.5-14b-instruct": 0.784,
+        "qwen2.5-32b-instruct": 0.8400000000000001,
+        "qwen2.5-72b-instruct": 0.8039999999999999,
+        "llama-3.1-8b-instruct": 0.30000000000000004,
+        "llama-3.1-70b-instruct": 0.568,
+        "llama-3.2-3b-instruct": 0.128,
+        "llama-3.3-70b-instruct": 0.612,
+        "mistral-large-instruct-2411": 0.76,
+        "gemma-2-27b-it": 0.504,
+        "gemma-2-9b-it": 0.18000000000000002,
+        "deepseek-v3": 0.968,
+        "deepseek-r1": 0.9359999999999999,
+        "qwq-32b": 0.924,
+        "Average": 0.5863999999999999
+    },
+    "TransdimensionalEnv": {
+        "qwen2.5-3b-instruct": 0.156,
+        "qwen2.5-7b-instruct": 0.38400000000000006,
+        "qwen2.5-14b-instruct": 0.836,
+        "qwen2.5-32b-instruct": 0.876,
+        "qwen2.5-72b-instruct": 0.836,
+        "llama-3.1-8b-instruct": 0.44399999999999995,
+        "llama-3.1-70b-instruct": 0.828,
+        "llama-3.2-3b-instruct": 0.172,
+        "llama-3.3-70b-instruct": 0.86,
+        "mistral-large-instruct-2411": 0.86,
+        "gemma-2-27b-it": 0.5599999999999999,
+        "gemma-2-9b-it": 0.516,
+        "deepseek-v3": 0.968,
+        "deepseek-r1": 0.9359999999999999,
+        "qwq-32b": 0.968,
+        "Average": 0.6799999999999999
+    },
+    "SorcererEnv": {
+        "qwen2.5-3b-instruct": 0.16,
+        "qwen2.5-7b-instruct": 0.32400000000000007,
+        "qwen2.5-14b-instruct": 0.8039999999999999,
+        "qwen2.5-32b-instruct": 0.8240000000000001,
+        "qwen2.5-72b-instruct": 0.8320000000000001,
+        "llama-3.1-8b-instruct": 0.276,
+        "llama-3.1-70b-instruct": 0.6639999999999999,
+        "llama-3.2-3b-instruct": 0.196,
+        "llama-3.3-70b-instruct": 0.7360000000000001,
+        "mistral-large-instruct-2411": 0.8,
+        "gemma-2-27b-it": 0.5640000000000001,
+        "gemma-2-9b-it": 0.28800000000000003,
+        "deepseek-v3": 0.8640000000000001,
+        "deepseek-r1": 0.8240000000000001,
+        "qwq-32b": 0.8400000000000001,
+        "Average": 0.5997333333333333
+    },
+    "QuantumEnv": {
+        "qwen2.5-3b-instruct": 0.196,
+        "qwen2.5-7b-instruct": 0.532,
+        "qwen2.5-14b-instruct": 0.8720000000000001,
+        "qwen2.5-32b-instruct": 0.9039999999999999,
+        "qwen2.5-72b-instruct": 0.916,
+        "llama-3.1-8b-instruct": 0.45600000000000007,
+        "llama-3.1-70b-instruct": 0.7999999999999999,
+        "llama-3.2-3b-instruct": 0.168,
+        "llama-3.3-70b-instruct": 0.8480000000000001,
+        "mistral-large-instruct-2411": 0.8720000000000001,
+        "gemma-2-27b-it": 0.744,
+        "gemma-2-9b-it": 0.544,
+        "deepseek-v3": 0.884,
+        "deepseek-r1": 0.8640000000000001,
+        "qwq-32b": 0.868,
+        "Average": 0.6978666666666666
+    },
+    "AstronomyEnv": {
+        "qwen2.5-3b-instruct": 0.172,
+        "qwen2.5-7b-instruct": 0.42800000000000005,
+        "qwen2.5-14b-instruct": 0.716,
+        "qwen2.5-32b-instruct": 0.676,
+        "qwen2.5-72b-instruct": 0.748,
+        "llama-3.1-8b-instruct": 0.336,
+        "llama-3.1-70b-instruct": 0.692,
+        "llama-3.2-3b-instruct": 0.176,
+        "llama-3.3-70b-instruct": 0.6519999999999999,
+        "mistral-large-instruct-2411": 0.7999999999999999,
+        "gemma-2-27b-it": 0.508,
+        "gemma-2-9b-it": 0.372,
+        "deepseek-v3": 0.748,
+        "deepseek-r1": 0.8200000000000001,
+        "qwq-32b": 0.852,
+        "Average": 0.5797333333333333
+    },
+    "MusicGenresEnv": {
+        "qwen2.5-3b-instruct": 0.22000000000000003,
+        "qwen2.5-7b-instruct": 0.42000000000000004,
+        "qwen2.5-14b-instruct": 0.72,
+        "qwen2.5-32b-instruct": 0.716,
+        "qwen2.5-72b-instruct": 0.696,
+        "llama-3.1-8b-instruct": 0.35200000000000004,
+        "llama-3.1-70b-instruct": 0.6280000000000001,
+        "llama-3.2-3b-instruct": 0.136,
+        "llama-3.3-70b-instruct": 0.592,
+        "mistral-large-instruct-2411": 0.732,
+        "gemma-2-27b-it": 0.44800000000000006,
+        "gemma-2-9b-it": 0.332,
+        "deepseek-v3": 0.748,
+        "deepseek-r1": 0.792,
+        "qwq-32b": 0.876,
+        "Average": 0.5605333333333334
+    },
+    "CloudEnv": {
+        "qwen2.5-3b-instruct": 0.21199999999999997,
+        "qwen2.5-7b-instruct": 0.42000000000000004,
+        "qwen2.5-14b-instruct": 0.76,
+        "qwen2.5-32b-instruct": 0.656,
+        "qwen2.5-72b-instruct": 0.712,
+        "llama-3.1-8b-instruct": 0.42000000000000004,
+        "llama-3.1-70b-instruct": 0.664,
+        "llama-3.2-3b-instruct": 0.22800000000000004,
+        "llama-3.3-70b-instruct": 0.696,
+        "mistral-large-instruct-2411": 0.8360000000000001,
+        "gemma-2-27b-it": 0.6,
+        "gemma-2-9b-it": 0.4,
+        "deepseek-v3": 0.8200000000000001,
+        "deepseek-r1": 0.908,
+        "qwq-32b": 0.9120000000000001,
+        "Average": 0.6162666666666667
+    },
+    "CuisineEnv": {
+        "qwen2.5-3b-instruct": 0.21600000000000003,
+        "qwen2.5-7b-instruct": 0.316,
+        "qwen2.5-14b-instruct": 0.6960000000000001,
+        "qwen2.5-32b-instruct": 0.664,
+        "qwen2.5-72b-instruct": 0.656,
+        "llama-3.1-8b-instruct": 0.22799999999999998,
+        "llama-3.1-70b-instruct": 0.476,
+        "llama-3.2-3b-instruct": 0.152,
+        "llama-3.3-70b-instruct": 0.44400000000000006,
+        "mistral-large-instruct-2411": 0.644,
+        "gemma-2-27b-it": 0.27599999999999997,
+        "gemma-2-9b-it": 0.156,
+        "deepseek-v3": 0.8400000000000001,
+        "deepseek-r1": 0.7959999999999999,
+        "qwq-32b": 0.8800000000000001,
+        "Average": 0.49599999999999994
+    },
+    "PlantEnv": {
+        "qwen2.5-3b-instruct": 0.168,
+        "qwen2.5-7b-instruct": 0.236,
+        "qwen2.5-14b-instruct": 0.34,
+        "qwen2.5-32b-instruct": 0.22000000000000003,
+        "qwen2.5-72b-instruct": 0.22799999999999998,
+        "llama-3.1-8b-instruct": 0.148,
+        "llama-3.1-70b-instruct": 0.16,
+        "llama-3.2-3b-instruct": 0.084,
+        "llama-3.3-70b-instruct": 0.07599999999999998,
+        "mistral-large-instruct-2411": 0.264,
+        "gemma-2-27b-it": 0.14400000000000002,
+        "gemma-2-9b-it": 0.092,
+        "deepseek-v3": 0.512,
+        "deepseek-r1": 0.5,
+        "qwq-32b": 0.548,
+        "Average": 0.24800000000000003
+    },
+    "HistoricalEnv": {
+        "qwen2.5-3b-instruct": 0.24,
+        "qwen2.5-7b-instruct": 0.368,
+        "qwen2.5-14b-instruct": 0.5800000000000001,
+        "qwen2.5-32b-instruct": 0.476,
+        "qwen2.5-72b-instruct": 0.512,
+        "llama-3.1-8b-instruct": 0.332,
+        "llama-3.1-70b-instruct": 0.616,
+        "llama-3.2-3b-instruct": 0.2,
+        "llama-3.3-70b-instruct": 0.652,
+        "mistral-large-instruct-2411": 0.6880000000000001,
+        "gemma-2-27b-it": 0.5,
+        "gemma-2-9b-it": 0.376,
+        "deepseek-v3": 0.748,
+        "deepseek-r1": 0.828,
+        "qwq-32b": 0.884,
+        "Average": 0.5333333333333334
+    },
+    "GadgetEnv": {
+        "qwen2.5-3b-instruct": 0.124,
+        "qwen2.5-7b-instruct": 0.312,
+        "qwen2.5-14b-instruct": 0.852,
+        "qwen2.5-32b-instruct": 0.8640000000000001,
+        "qwen2.5-72b-instruct": 0.892,
+        "llama-3.1-8b-instruct": 0.284,
+        "llama-3.1-70b-instruct": 0.692,
+        "llama-3.2-3b-instruct": 0.11200000000000002,
+        "llama-3.3-70b-instruct": 0.7360000000000001,
+        "mistral-large-instruct-2411": 0.884,
+        "gemma-2-27b-it": 0.32799999999999996,
+        "gemma-2-9b-it": 0.184,
+        "deepseek-v3": 0.9640000000000001,
+        "deepseek-r1": 0.932,
+        "qwq-32b": 0.932,
+        "Average": 0.6061333333333334
+    },
+    "TimeTravelEnv": {
+        "qwen2.5-3b-instruct": 0.128,
+        "qwen2.5-7b-instruct": 0.292,
+        "qwen2.5-14b-instruct": 0.808,
+        "qwen2.5-32b-instruct": 0.828,
+        "qwen2.5-72b-instruct": 0.8039999999999999,
+        "llama-3.1-8b-instruct": 0.376,
+        "llama-3.1-70b-instruct": 0.684,
+        "llama-3.2-3b-instruct": 0.124,
+        "llama-3.3-70b-instruct": 0.716,
+        "mistral-large-instruct-2411": 0.884,
+        "gemma-2-27b-it": 0.32799999999999996,
+        "gemma-2-9b-it": 0.21600000000000003,
+        "deepseek-v3": 0.9399999999999998,
+        "deepseek-r1": 0.932,
+        "qwq-32b": 0.924,
+        "Average": 0.5989333333333333
+    },
+    "PollutionEnv": {
+        "qwen2.5-3b-instruct": 0.136,
+        "qwen2.5-7b-instruct": 0.328,
+        "qwen2.5-14b-instruct": 0.792,
+        "qwen2.5-32b-instruct": 0.7120000000000001,
+        "qwen2.5-72b-instruct": 0.704,
+        "llama-3.1-8b-instruct": 0.316,
+        "llama-3.1-70b-instruct": 0.664,
+        "llama-3.2-3b-instruct": 0.124,
+        "llama-3.3-70b-instruct": 0.6960000000000001,
+        "mistral-large-instruct-2411": 0.784,
+        "gemma-2-27b-it": 0.336,
+        "gemma-2-9b-it": 0.252,
+        "deepseek-v3": 0.8640000000000001,
+        "deepseek-r1": 0.8560000000000001,
+        "qwq-32b": 0.852,
+        "Average": 0.5610666666666666
+    },
+    "DemographicEnv": {
+        "qwen2.5-3b-instruct": 0.072,
+        "qwen2.5-7b-instruct": 0.42800000000000005,
+        "qwen2.5-14b-instruct": 0.68,
+        "qwen2.5-32b-instruct": 0.7799999999999999,
+        "qwen2.5-72b-instruct": 0.7719999999999999,
+        "llama-3.1-8b-instruct": 0.272,
+        "llama-3.1-70b-instruct": 0.6239999999999999,
+        "llama-3.2-3b-instruct": 0.176,
+        "llama-3.3-70b-instruct": 0.748,
+        "mistral-large-instruct-2411": 0.8200000000000001,
+        "gemma-2-27b-it": 0.356,
+        "gemma-2-9b-it": 0.156,
+        "deepseek-v3": 0.8960000000000001,
+        "deepseek-r1": 0.876,
+        "qwq-32b": 0.8960000000000001,
+        "Average": 0.5701333333333333
+    },
+    "GeneticEnv": {
+        "qwen2.5-3b-instruct": 0.084,
+        "qwen2.5-7b-instruct": 0.392,
+        "qwen2.5-14b-instruct": 0.884,
+        "qwen2.5-32b-instruct": 0.9279999999999999,
+        "qwen2.5-72b-instruct": 0.9400000000000001,
+        "llama-3.1-8b-instruct": 0.45999999999999996,
+        "llama-3.1-70b-instruct": 0.9,
+        "llama-3.2-3b-instruct": 0.192,
+        "llama-3.3-70b-instruct": 0.916,
+        "mistral-large-instruct-2411": 0.9040000000000001,
+        "gemma-2-27b-it": 0.776,
+        "gemma-2-9b-it": 0.548,
+        "deepseek-v3": 0.984,
+        "deepseek-r1": 0.952,
+        "qwq-32b": 0.932,
+        "Average": 0.7194666666666667
+    },
+    "CraftsmanEnv": {
+        "qwen2.5-3b-instruct": 0.14400000000000002,
+        "qwen2.5-7b-instruct": 0.256,
+        "qwen2.5-14b-instruct": 0.624,
+        "qwen2.5-32b-instruct": 0.736,
+        "qwen2.5-72b-instruct": 0.664,
+        "llama-3.1-8b-instruct": 0.22000000000000003,
+        "llama-3.1-70b-instruct": 0.524,
+        "llama-3.2-3b-instruct": 0.10800000000000001,
+        "llama-3.3-70b-instruct": 0.41600000000000004,
+        "mistral-large-instruct-2411": 0.7080000000000001,
+        "gemma-2-27b-it": 0.324,
+        "gemma-2-9b-it": 0.096,
+        "deepseek-v3": 0.9,
+        "deepseek-r1": 0.7879999999999999,
+        "qwq-32b": 0.8160000000000001,
+        "Average": 0.4882666666666667
+    },
+    "StarConstellationEnv": {
+        "qwen2.5-3b-instruct": 0.1,
+        "qwen2.5-7b-instruct": 0.332,
+        "qwen2.5-14b-instruct": 0.5960000000000001,
+        "qwen2.5-32b-instruct": 0.572,
+        "qwen2.5-72b-instruct": 0.5840000000000001,
+        "llama-3.1-8b-instruct": 0.376,
+        "llama-3.1-70b-instruct": 0.4640000000000001,
+        "llama-3.2-3b-instruct": 0.136,
+        "llama-3.3-70b-instruct": 0.41200000000000003,
+        "mistral-large-instruct-2411": 0.6120000000000001,
+        "gemma-2-27b-it": 0.472,
+        "gemma-2-9b-it": 0.22799999999999998,
+        "deepseek-v3": 0.744,
+        "deepseek-r1": 0.748,
+        "qwq-32b": 0.736,
+        "Average": 0.47413333333333335
+    },
+    "MythicalCreatureEnv": {
+        "qwen2.5-3b-instruct": 0.2,
+        "qwen2.5-7b-instruct": 0.324,
+        "qwen2.5-14b-instruct": 0.632,
+        "qwen2.5-32b-instruct": 0.712,
+        "qwen2.5-72b-instruct": 0.668,
+        "llama-3.1-8b-instruct": 0.31200000000000006,
+        "llama-3.1-70b-instruct": 0.62,
+        "llama-3.2-3b-instruct": 0.11200000000000002,
+        "llama-3.3-70b-instruct": 0.648,
+        "mistral-large-instruct-2411": 0.7480000000000001,
+        "gemma-2-27b-it": 0.42799999999999994,
+        "gemma-2-9b-it": 0.268,
+        "deepseek-v3": 0.8400000000000001,
+        "deepseek-r1": 0.8400000000000001,
+        "qwq-32b": 0.852,
+        "Average": 0.5469333333333333
+    },
+    "ArtStyleEnv": {
+        "qwen2.5-3b-instruct": 0.136,
+        "qwen2.5-7b-instruct": 0.332,
+        "qwen2.5-14b-instruct": 0.78,
+        "qwen2.5-32b-instruct": 0.8320000000000001,
+        "qwen2.5-72b-instruct": 0.748,
+        "llama-3.1-8b-instruct": 0.356,
+        "llama-3.1-70b-instruct": 0.616,
+        "llama-3.2-3b-instruct": 0.17200000000000001,
+        "llama-3.3-70b-instruct": 0.6199999999999999,
+        "mistral-large-instruct-2411": 0.828,
+        "gemma-2-27b-it": 0.43200000000000005,
+        "gemma-2-9b-it": 0.256,
+        "deepseek-v3": 0.876,
+        "deepseek-r1": 0.8200000000000001,
+        "qwq-32b": 0.868,
+        "Average": 0.5781333333333335
+    },
+    "CookingEnv": {
+        "qwen2.5-3b-instruct": 0.13999999999999999,
+        "qwen2.5-7b-instruct": 0.44799999999999995,
+        "qwen2.5-14b-instruct": 0.76,
+        "qwen2.5-32b-instruct": 0.7440000000000001,
+        "qwen2.5-72b-instruct": 0.7,
+        "llama-3.1-8b-instruct": 0.364,
+        "llama-3.1-70b-instruct": 0.6839999999999999,
+        "llama-3.2-3b-instruct": 0.156,
+        "llama-3.3-70b-instruct": 0.656,
+        "mistral-large-instruct-2411": 0.74,
+        "gemma-2-27b-it": 0.48,
+        "gemma-2-9b-it": 0.364,
+        "deepseek-v3": 0.8640000000000001,
+        "deepseek-r1": 0.812,
+        "qwq-32b": 0.9,
+        "Average": 0.5874666666666666
+    },
+    "HistoricalBattleEnv": {
+        "qwen2.5-3b-instruct": 0.256,
+        "qwen2.5-7b-instruct": 0.292,
+        "qwen2.5-14b-instruct": 0.45999999999999996,
+        "qwen2.5-32b-instruct": 0.476,
+        "qwen2.5-72b-instruct": 0.42400000000000004,
+        "llama-3.1-8b-instruct": 0.28400000000000003,
+        "llama-3.1-70b-instruct": 0.492,
+        "llama-3.2-3b-instruct": 0.148,
+        "llama-3.3-70b-instruct": 0.62,
+        "mistral-large-instruct-2411": 0.608,
+        "gemma-2-27b-it": 0.388,
+        "gemma-2-9b-it": 0.34,
+        "deepseek-v3": 0.724,
+        "deepseek-r1": 0.788,
+        "qwq-32b": 0.8560000000000001,
+        "Average": 0.47706666666666664
+    },
+    "FungalEnv": {
+        "qwen2.5-3b-instruct": 0.15999999999999998,
+        "qwen2.5-7b-instruct": 0.46399999999999997,
+        "qwen2.5-14b-instruct": 0.664,
+        "qwen2.5-32b-instruct": 0.728,
+        "qwen2.5-72b-instruct": 0.6839999999999999,
+        "llama-3.1-8b-instruct": 0.41600000000000004,
+        "llama-3.1-70b-instruct": 0.5840000000000001,
+        "llama-3.2-3b-instruct": 0.14,
+        "llama-3.3-70b-instruct": 0.644,
+        "mistral-large-instruct-2411": 0.7440000000000001,
+        "gemma-2-27b-it": 0.536,
+        "gemma-2-9b-it": 0.184,
+        "deepseek-v3": 0.844,
+        "deepseek-r1": 0.764,
+        "qwq-32b": 0.7879999999999999,
+        "Average": 0.5562666666666666
+    },
+    "CryptographyEnv": {
+        "qwen2.5-3b-instruct": 0.24000000000000005,
+        "qwen2.5-7b-instruct": 0.23199999999999998,
+        "qwen2.5-14b-instruct": 0.508,
+        "qwen2.5-32b-instruct": 0.5760000000000001,
+        "qwen2.5-72b-instruct": 0.528,
+        "llama-3.1-8b-instruct": 0.29600000000000004,
+        "llama-3.1-70b-instruct": 0.524,
+        "llama-3.2-3b-instruct": 0.11600000000000002,
+        "llama-3.3-70b-instruct": 0.512,
+        "mistral-large-instruct-2411": 0.6799999999999999,
+        "gemma-2-27b-it": 0.328,
+        "gemma-2-9b-it": 0.192,
+        "deepseek-v3": 0.784,
+        "deepseek-r1": 0.74,
+        "qwq-32b": 0.8480000000000001,
+        "Average": 0.4736
+    },
+    "StorageEnv": {
+        "qwen2.5-3b-instruct": 0.22800000000000004,
+        "qwen2.5-7b-instruct": 0.44000000000000006,
+        "qwen2.5-14b-instruct": 0.852,
+        "qwen2.5-32b-instruct": 0.884,
+        "qwen2.5-72b-instruct": 0.8119999999999999,
+        "llama-3.1-8b-instruct": 0.34800000000000003,
+        "llama-3.1-70b-instruct": 0.724,
+        "llama-3.2-3b-instruct": 0.21600000000000003,
+        "llama-3.3-70b-instruct": 0.796,
+        "mistral-large-instruct-2411": 0.8880000000000001,
+        "gemma-2-27b-it": 0.596,
+        "gemma-2-9b-it": 0.392,
+        "deepseek-v3": 0.9640000000000001,
+        "deepseek-r1": 0.9119999999999999,
+        "qwq-32b": 0.944,
+        "Average": 0.6663999999999999
+    },
+    "RoverEnv": {
+        "qwen2.5-3b-instruct": 0.14400000000000002,
+        "qwen2.5-7b-instruct": 0.236,
+        "qwen2.5-14b-instruct": 0.8480000000000001,
+        "qwen2.5-32b-instruct": 0.8360000000000001,
+        "qwen2.5-72b-instruct": 0.796,
+        "llama-3.1-8b-instruct": 0.28400000000000003,
+        "llama-3.1-70b-instruct": 0.612,
+        "llama-3.2-3b-instruct": 0.148,
+        "llama-3.3-70b-instruct": 0.724,
+        "mistral-large-instruct-2411": 0.828,
+        "gemma-2-27b-it": 0.4600000000000001,
+        "gemma-2-9b-it": 0.072,
+        "deepseek-v3": 0.9200000000000002,
+        "deepseek-r1": 0.9,
+        "qwq-32b": 0.8720000000000001,
+        "Average": 0.5786666666666668
+    },
+    "FashionEnv": {
+        "qwen2.5-3b-instruct": 0.17200000000000001,
+        "qwen2.5-7b-instruct": 0.304,
+        "qwen2.5-14b-instruct": 0.8240000000000001,
+        "qwen2.5-32b-instruct": 0.808,
+        "qwen2.5-72b-instruct": 0.768,
+        "llama-3.1-8b-instruct": 0.32,
+        "llama-3.1-70b-instruct": 0.6,
+        "llama-3.2-3b-instruct": 0.16399999999999998,
+        "llama-3.3-70b-instruct": 0.6160000000000001,
+        "mistral-large-instruct-2411": 0.756,
+        "gemma-2-27b-it": 0.524,
+        "gemma-2-9b-it": 0.292,
+        "deepseek-v3": 0.86,
+        "deepseek-r1": 0.756,
+        "qwq-32b": 0.86,
+        "Average": 0.5749333333333334
+    },
+    "LicenseEnv": {
+        "qwen2.5-3b-instruct": 0.196,
+        "qwen2.5-7b-instruct": 0.29200000000000004,
+        "qwen2.5-14b-instruct": 0.556,
+        "qwen2.5-32b-instruct": 0.44000000000000006,
+        "qwen2.5-72b-instruct": 0.484,
+        "llama-3.1-8b-instruct": 0.26,
+        "llama-3.1-70b-instruct": 0.496,
+        "llama-3.2-3b-instruct": 0.072,
+        "llama-3.3-70b-instruct": 0.45999999999999996,
+        "mistral-large-instruct-2411": 0.504,
+        "gemma-2-27b-it": 0.37600000000000006,
+        "gemma-2-9b-it": 0.296,
+        "deepseek-v3": 0.556,
+        "deepseek-r1": 0.52,
+        "qwq-32b": 0.5800000000000001,
+        "Average": 0.4058666666666667
+    },
+    "VirusClassificationEnv": {
+        "qwen2.5-3b-instruct": 0.22000000000000003,
+        "qwen2.5-7b-instruct": 0.28,
+        "qwen2.5-14b-instruct": 0.384,
+        "qwen2.5-32b-instruct": 0.38,
+        "qwen2.5-72b-instruct": 0.42800000000000005,
+        "llama-3.1-8b-instruct": 0.256,
+        "llama-3.1-70b-instruct": 0.332,
+        "llama-3.2-3b-instruct": 0.156,
+        "llama-3.3-70b-instruct": 0.396,
+        "mistral-large-instruct-2411": 0.532,
+        "gemma-2-27b-it": 0.34,
+        "gemma-2-9b-it": 0.31200000000000006,
+        "deepseek-v3": 0.536,
+        "deepseek-r1": 0.64,
+        "qwq-32b": 0.684,
+        "Average": 0.3917333333333333
+    },
+    "TestingEnv": {
+        "qwen2.5-3b-instruct": 0.19200000000000003,
+        "qwen2.5-7b-instruct": 0.22000000000000003,
+        "qwen2.5-14b-instruct": 0.608,
+        "qwen2.5-32b-instruct": 0.648,
+        "qwen2.5-72b-instruct": 0.708,
+        "llama-3.1-8b-instruct": 0.332,
+        "llama-3.1-70b-instruct": 0.68,
+        "llama-3.2-3b-instruct": 0.17200000000000001,
+        "llama-3.3-70b-instruct": 0.7040000000000001,
+        "mistral-large-instruct-2411": 0.764,
+        "gemma-2-27b-it": 0.22799999999999998,
+        "gemma-2-9b-it": 0.26,
+        "deepseek-v3": 0.8880000000000001,
+        "deepseek-r1": 0.764,
+        "qwq-32b": 0.7999999999999999,
+        "Average": 0.5312
+    },
+    "NarrativeDetectEnv": {
+        "qwen2.5-3b-instruct": 0.148,
+        "qwen2.5-7b-instruct": 0.30000000000000004,
+        "qwen2.5-14b-instruct": 0.552,
+        "qwen2.5-32b-instruct": 0.8440000000000001,
+        "qwen2.5-72b-instruct": 0.76,
+        "llama-3.1-8b-instruct": 0.28800000000000003,
+        "llama-3.1-70b-instruct": 0.6279999999999999,
+        "llama-3.2-3b-instruct": 0.10400000000000001,
+        "llama-3.3-70b-instruct": 0.704,
+        "mistral-large-instruct-2411": 0.7919999999999999,
+        "gemma-2-27b-it": 0.328,
+        "gemma-2-9b-it": 0.192,
+        "deepseek-v3": 0.8560000000000001,
+        "deepseek-r1": 0.748,
+        "qwq-32b": 0.784,
+        "Average": 0.5352
+    },
+    "RenewableEnergyEnv": {
+        "qwen2.5-3b-instruct": 0.184,
+        "qwen2.5-7b-instruct": 0.44399999999999995,
+        "qwen2.5-14b-instruct": 0.648,
+        "qwen2.5-32b-instruct": 0.932,
+        "qwen2.5-72b-instruct": 0.8880000000000001,
+        "llama-3.1-8b-instruct": 0.396,
+        "llama-3.1-70b-instruct": 0.812,
+        "llama-3.2-3b-instruct": 0.2,
+        "llama-3.3-70b-instruct": 0.8240000000000001,
+        "mistral-large-instruct-2411": 0.8560000000000001,
+        "gemma-2-27b-it": 0.348,
+        "gemma-2-9b-it": 0.188,
+        "deepseek-v3": 0.96,
+        "deepseek-r1": 0.9800000000000001,
+        "qwq-32b": 0.9800000000000001,
+        "Average": 0.6426666666666667
+    },
+    "CelestialEnv": {
+        "qwen2.5-3b-instruct": 0.20400000000000001,
+        "qwen2.5-7b-instruct": 0.252,
+        "qwen2.5-14b-instruct": 0.728,
+        "qwen2.5-32b-instruct": 0.792,
+        "qwen2.5-72b-instruct": 0.7239999999999999,
+        "llama-3.1-8b-instruct": 0.256,
+        "llama-3.1-70b-instruct": 0.6920000000000001,
+        "llama-3.2-3b-instruct": 0.192,
+        "llama-3.3-70b-instruct": 0.744,
+        "mistral-large-instruct-2411": 0.82,
+        "gemma-2-27b-it": 0.528,
+        "gemma-2-9b-it": 0.344,
+        "deepseek-v3": 0.8480000000000001,
+        "deepseek-r1": 0.8360000000000001,
+        "qwq-32b": 0.8879999999999999,
+        "Average": 0.5898666666666668
+    },
+    "SpiceEnv": {
+        "qwen2.5-3b-instruct": 0.21199999999999997,
+        "qwen2.5-7b-instruct": 0.332,
+        "qwen2.5-14b-instruct": 0.672,
+        "qwen2.5-32b-instruct": 0.476,
+        "qwen2.5-72b-instruct": 0.5880000000000001,
+        "llama-3.1-8b-instruct": 0.32799999999999996,
+        "llama-3.1-70b-instruct": 0.40800000000000003,
+        "llama-3.2-3b-instruct": 0.22000000000000003,
+        "llama-3.3-70b-instruct": 0.336,
+        "mistral-large-instruct-2411": 0.5800000000000001,
+        "gemma-2-27b-it": 0.28400000000000003,
+        "gemma-2-9b-it": 0.172,
+        "deepseek-v3": 0.908,
+        "deepseek-r1": 0.7679999999999999,
+        "qwq-32b": 0.8720000000000001,
+        "Average": 0.47706666666666664
+    },
+    "WildlifeEnv": {
+        "qwen2.5-3b-instruct": 0.21600000000000003,
+        "qwen2.5-7b-instruct": 0.352,
+        "qwen2.5-14b-instruct": 0.644,
+        "qwen2.5-32b-instruct": 0.592,
+        "qwen2.5-72b-instruct": 0.616,
+        "llama-3.1-8b-instruct": 0.316,
+        "llama-3.1-70b-instruct": 0.544,
+        "llama-3.2-3b-instruct": 0.23199999999999998,
+        "llama-3.3-70b-instruct": 0.616,
+        "mistral-large-instruct-2411": 0.628,
+        "gemma-2-27b-it": 0.45199999999999996,
+        "gemma-2-9b-it": 0.344,
+        "deepseek-v3": 0.736,
+        "deepseek-r1": 0.6040000000000001,
+        "qwq-32b": 0.716,
+        "Average": 0.5072
+    },
+    "VehicleEnv": {
+        "qwen2.5-3b-instruct": 0.172,
+        "qwen2.5-7b-instruct": 0.308,
+        "qwen2.5-14b-instruct": 0.54,
+        "qwen2.5-32b-instruct": 0.776,
+        "qwen2.5-72b-instruct": 0.78,
+        "llama-3.1-8b-instruct": 0.248,
+        "llama-3.1-70b-instruct": 0.62,
+        "llama-3.2-3b-instruct": 0.152,
+        "llama-3.3-70b-instruct": 0.6960000000000001,
+        "mistral-large-instruct-2411": 0.8800000000000001,
+        "gemma-2-27b-it": 0.44799999999999995,
+        "gemma-2-9b-it": 0.248,
+        "deepseek-v3": 0.9199999999999999,
+        "deepseek-r1": 0.9199999999999999,
+        "qwq-32b": 0.916,
+        "Average": 0.5749333333333333
+    },
+    "BeverageEnv": {
+        "qwen2.5-3b-instruct": 0.128,
+        "qwen2.5-7b-instruct": 0.296,
+        "qwen2.5-14b-instruct": 0.792,
+        "qwen2.5-32b-instruct": 0.6880000000000001,
+        "qwen2.5-72b-instruct": 0.724,
+        "llama-3.1-8b-instruct": 0.41200000000000003,
+        "llama-3.1-70b-instruct": 0.6199999999999999,
+        "llama-3.2-3b-instruct": 0.16399999999999998,
+        "llama-3.3-70b-instruct": 0.5800000000000001,
+        "mistral-large-instruct-2411": 0.748,
+        "gemma-2-27b-it": 0.40800000000000003,
+        "gemma-2-9b-it": 0.296,
+        "deepseek-v3": 0.8800000000000001,
+        "deepseek-r1": 0.7520000000000001,
+        "qwq-32b": 0.844,
+        "Average": 0.5554666666666667
+    },
+    "ControlEnv": {
+        "qwen2.5-3b-instruct": 0.12800000000000003,
+        "qwen2.5-7b-instruct": 0.364,
+        "qwen2.5-14b-instruct": 0.68,
+        "qwen2.5-32b-instruct": 0.8320000000000001,
+        "qwen2.5-72b-instruct": 0.8400000000000001,
+        "llama-3.1-8b-instruct": 0.364,
+        "llama-3.1-70b-instruct": 0.656,
+        "llama-3.2-3b-instruct": 0.15599999999999997,
+        "llama-3.3-70b-instruct": 0.6320000000000001,
+        "mistral-large-instruct-2411": 0.784,
+        "gemma-2-27b-it": 0.4640000000000001,
+        "gemma-2-9b-it": 0.18,
+        "deepseek-v3": 0.9119999999999999,
+        "deepseek-r1": 0.9119999999999999,
+        "qwq-32b": 0.932,
+        "Average": 0.5890666666666665
+    },
+    "CurrencyEnv": {
+        "qwen2.5-3b-instruct": 0.252,
+        "qwen2.5-7b-instruct": 0.392,
+        "qwen2.5-14b-instruct": 0.8560000000000001,
+        "qwen2.5-32b-instruct": 0.884,
+        "qwen2.5-72b-instruct": 0.836,
+        "llama-3.1-8b-instruct": 0.476,
+        "llama-3.1-70b-instruct": 0.7520000000000001,
+        "llama-3.2-3b-instruct": 0.22400000000000003,
+        "llama-3.3-70b-instruct": 0.7000000000000001,
+        "mistral-large-instruct-2411": 0.8960000000000001,
+        "gemma-2-27b-it": 0.68,
+        "gemma-2-9b-it": 0.196,
+        "deepseek-v3": 0.9800000000000001,
+        "deepseek-r1": 0.932,
+        "qwq-32b": 0.9640000000000001,
+        "Average": 0.668
+    },
+    "MarketingEnv": {
+        "qwen2.5-3b-instruct": 0.12,
+        "qwen2.5-7b-instruct": 0.34400000000000003,
+        "qwen2.5-14b-instruct": 0.524,
+        "qwen2.5-32b-instruct": 0.7479999999999999,
+        "qwen2.5-72b-instruct": 0.732,
+        "llama-3.1-8b-instruct": 0.30800000000000005,
+        "llama-3.1-70b-instruct": 0.7040000000000001,
+        "llama-3.2-3b-instruct": 0.14400000000000002,
+        "llama-3.3-70b-instruct": 0.7639999999999999,
+        "mistral-large-instruct-2411": 0.7600000000000001,
+        "gemma-2-27b-it": 0.32400000000000007,
+        "gemma-2-9b-it": 0.184,
+        "deepseek-v3": 0.812,
+        "deepseek-r1": 0.7959999999999999,
+        "qwq-32b": 0.8320000000000001,
+        "Average": 0.5397333333333333
+    },
+    "BotanicalEnv": {
+        "qwen2.5-3b-instruct": 0.18800000000000003,
+        "qwen2.5-7b-instruct": 0.316,
+        "qwen2.5-14b-instruct": 0.9119999999999999,
+        "qwen2.5-32b-instruct": 0.884,
+        "qwen2.5-72b-instruct": 0.9039999999999999,
+        "llama-3.1-8b-instruct": 0.4119999999999999,
+        "llama-3.1-70b-instruct": 0.836,
+        "llama-3.2-3b-instruct": 0.23600000000000004,
+        "llama-3.3-70b-instruct": 0.8480000000000001,
+        "mistral-large-instruct-2411": 0.8640000000000001,
+        "gemma-2-27b-it": 0.604,
+        "gemma-2-9b-it": 0.264,
+        "deepseek-v3": 0.9040000000000001,
+        "deepseek-r1": 0.9399999999999998,
+        "qwq-32b": 0.968,
+        "Average": 0.672
+    },
+    "CircusActEnv": {
+        "qwen2.5-3b-instruct": 0.17200000000000001,
+        "qwen2.5-7b-instruct": 0.32399999999999995,
+        "qwen2.5-14b-instruct": 0.64,
+        "qwen2.5-32b-instruct": 0.712,
+        "qwen2.5-72b-instruct": 0.768,
+        "llama-3.1-8b-instruct": 0.276,
+        "llama-3.1-70b-instruct": 0.648,
+        "llama-3.2-3b-instruct": 0.176,
+        "llama-3.3-70b-instruct": 0.62,
+        "mistral-large-instruct-2411": 0.748,
+        "gemma-2-27b-it": 0.384,
+        "gemma-2-9b-it": 0.29600000000000004,
+        "deepseek-v3": 0.8640000000000001,
+        "deepseek-r1": 0.82,
+        "qwq-32b": 0.8720000000000001,
+        "Average": 0.5546666666666668
+    },
+    "AudioDialectEnv": {
+        "qwen2.5-3b-instruct": 0.128,
+        "qwen2.5-7b-instruct": 0.312,
+        "qwen2.5-14b-instruct": 0.5800000000000001,
+        "qwen2.5-32b-instruct": 0.6,
+        "qwen2.5-72b-instruct": 0.528,
+        "llama-3.1-8b-instruct": 0.21600000000000003,
+        "llama-3.1-70b-instruct": 0.4,
+        "llama-3.2-3b-instruct": 0.132,
+        "llama-3.3-70b-instruct": 0.32399999999999995,
+        "mistral-large-instruct-2411": 0.68,
+        "gemma-2-27b-it": 0.28,
+        "gemma-2-9b-it": 0.11600000000000002,
+        "deepseek-v3": 0.7520000000000001,
+        "deepseek-r1": 0.7919999999999999,
+        "qwq-32b": 0.8119999999999999,
+        "Average": 0.4434666666666666
+    },
+    "LeadershipEnv": {
+        "qwen2.5-3b-instruct": 0.164,
+        "qwen2.5-7b-instruct": 0.372,
+        "qwen2.5-14b-instruct": 0.7,
+        "qwen2.5-32b-instruct": 0.732,
+        "qwen2.5-72b-instruct": 0.7639999999999999,
+        "llama-3.1-8b-instruct": 0.364,
+        "llama-3.1-70b-instruct": 0.708,
+        "llama-3.2-3b-instruct": 0.128,
+        "llama-3.3-70b-instruct": 0.6920000000000001,
+        "mistral-large-instruct-2411": 0.728,
+        "gemma-2-27b-it": 0.46799999999999997,
+        "gemma-2-9b-it": 0.20400000000000001,
+        "deepseek-v3": 0.8200000000000001,
+        "deepseek-r1": 0.748,
+        "qwq-32b": 0.828,
+        "Average": 0.5613333333333334
+    },
+    "TransportEnv": {
+        "qwen2.5-3b-instruct": 0.196,
+        "qwen2.5-7b-instruct": 0.372,
+        "qwen2.5-14b-instruct": 0.716,
+        "qwen2.5-32b-instruct": 0.732,
+        "qwen2.5-72b-instruct": 0.8,
+        "llama-3.1-8b-instruct": 0.316,
+        "llama-3.1-70b-instruct": 0.648,
+        "llama-3.2-3b-instruct": 0.15200000000000002,
+        "llama-3.3-70b-instruct": 0.6000000000000001,
+        "mistral-large-instruct-2411": 0.7879999999999999,
+        "gemma-2-27b-it": 0.44399999999999995,
+        "gemma-2-9b-it": 0.364,
+        "deepseek-v3": 0.8640000000000001,
+        "deepseek-r1": 0.8240000000000001,
+        "qwq-32b": 0.9199999999999999,
+        "Average": 0.5824
+    },
+    "EcologicalEnv": {
+        "qwen2.5-3b-instruct": 0.152,
+        "qwen2.5-7b-instruct": 0.45600000000000007,
+        "qwen2.5-14b-instruct": 0.748,
+        "qwen2.5-32b-instruct": 0.82,
+        "qwen2.5-72b-instruct": 0.792,
+        "llama-3.1-8b-instruct": 0.42000000000000004,
+        "llama-3.1-70b-instruct": 0.692,
+        "llama-3.2-3b-instruct": 0.21600000000000003,
+        "llama-3.3-70b-instruct": 0.64,
+        "mistral-large-instruct-2411": 0.772,
+        "gemma-2-27b-it": 0.5680000000000001,
+        "gemma-2-9b-it": 0.46799999999999997,
+        "deepseek-v3": 0.868,
+        "deepseek-r1": 0.8720000000000001,
+        "qwq-32b": 0.8879999999999999,
+        "Average": 0.6248
+    },
+    "MythicEnv": {
+        "qwen2.5-3b-instruct": 0.132,
+        "qwen2.5-7b-instruct": 0.36,
+        "qwen2.5-14b-instruct": 0.744,
+        "qwen2.5-32b-instruct": 0.74,
+        "qwen2.5-72b-instruct": 0.672,
+        "llama-3.1-8b-instruct": 0.236,
+        "llama-3.1-70b-instruct": 0.596,
+        "llama-3.2-3b-instruct": 0.12,
+        "llama-3.3-70b-instruct": 0.576,
+        "mistral-large-instruct-2411": 0.6960000000000001,
+        "gemma-2-27b-it": 0.45599999999999996,
+        "gemma-2-9b-it": 0.136,
+        "deepseek-v3": 0.8960000000000001,
+        "deepseek-r1": 0.8720000000000001,
+        "qwq-32b": 0.8400000000000001,
+        "Average": 0.5381333333333332
+    },
+    "EnzymeEnv": {
+        "qwen2.5-3b-instruct": 0.252,
+        "qwen2.5-7b-instruct": 0.43200000000000005,
+        "qwen2.5-14b-instruct": 0.636,
+        "qwen2.5-32b-instruct": 0.676,
+        "qwen2.5-72b-instruct": 0.676,
+        "llama-3.1-8b-instruct": 0.316,
+        "llama-3.1-70b-instruct": 0.552,
+        "llama-3.2-3b-instruct": 0.192,
+        "llama-3.3-70b-instruct": 0.5640000000000001,
+        "mistral-large-instruct-2411": 0.732,
+        "gemma-2-27b-it": 0.43600000000000005,
+        "gemma-2-9b-it": 0.264,
+        "deepseek-v3": 0.8400000000000001,
+        "deepseek-r1": 0.76,
+        "qwq-32b": 0.804,
+        "Average": 0.5421333333333334
+    },
+    "OSKernelEnv": {
+        "qwen2.5-3b-instruct": 0.192,
+        "qwen2.5-7b-instruct": 0.28400000000000003,
+        "qwen2.5-14b-instruct": 0.8119999999999999,
+        "qwen2.5-32b-instruct": 0.784,
+        "qwen2.5-72b-instruct": 0.788,
+        "llama-3.1-8b-instruct": 0.316,
+        "llama-3.1-70b-instruct": 0.6920000000000001,
+        "llama-3.2-3b-instruct": 0.128,
+        "llama-3.3-70b-instruct": 0.74,
+        "mistral-large-instruct-2411": 0.8559999999999999,
+        "gemma-2-27b-it": 0.46399999999999997,
+        "gemma-2-9b-it": 0.2,
+        "deepseek-v3": 0.9480000000000001,
+        "deepseek-r1": 0.96,
+        "qwq-32b": 0.984,
+        "Average": 0.6098666666666668
+    },
+    "MineralClassificationEnv": {
+        "qwen2.5-3b-instruct": 0.11600000000000002,
+        "qwen2.5-7b-instruct": 0.248,
+        "qwen2.5-14b-instruct": 0.8320000000000001,
+        "qwen2.5-32b-instruct": 0.9040000000000001,
+        "qwen2.5-72b-instruct": 0.884,
+        "llama-3.1-8b-instruct": 0.384,
+        "llama-3.1-70b-instruct": 0.8240000000000001,
+        "llama-3.2-3b-instruct": 0.14800000000000002,
+        "llama-3.3-70b-instruct": 0.8960000000000001,
+        "mistral-large-instruct-2411": 0.908,
+        "gemma-2-27b-it": 0.508,
+        "gemma-2-9b-it": 0.268,
+        "deepseek-v3": 0.984,
+        "deepseek-r1": 0.9199999999999999,
+        "qwq-32b": 0.9640000000000001,
+        "Average": 0.6525333333333333
+    },
+    "EconomicEnv": {
+        "qwen2.5-3b-instruct": 0.136,
+        "qwen2.5-7b-instruct": 0.24,
+        "qwen2.5-14b-instruct": 0.8560000000000001,
+        "qwen2.5-32b-instruct": 0.9199999999999999,
+        "qwen2.5-72b-instruct": 0.8960000000000001,
+        "llama-3.1-8b-instruct": 0.43600000000000005,
+        "llama-3.1-70b-instruct": 0.808,
+        "llama-3.2-3b-instruct": 0.152,
+        "llama-3.3-70b-instruct": 0.8240000000000001,
+        "mistral-large-instruct-2411": 0.924,
+        "gemma-2-27b-it": 0.45199999999999996,
+        "gemma-2-9b-it": 0.36,
+        "deepseek-v3": 0.9559999999999998,
+        "deepseek-r1": 0.9359999999999999,
+        "qwq-32b": 0.9719999999999999,
+        "Average": 0.6578666666666667
+    },
+    "DetectiveEnv": {
+        "qwen2.5-3b-instruct": 0.168,
+        "qwen2.5-7b-instruct": 0.38,
+        "qwen2.5-14b-instruct": 0.836,
+        "qwen2.5-32b-instruct": 0.884,
+        "qwen2.5-72b-instruct": 0.8480000000000001,
+        "llama-3.1-8b-instruct": 0.34800000000000003,
+        "llama-3.1-70b-instruct": 0.74,
+        "llama-3.2-3b-instruct": 0.248,
+        "llama-3.3-70b-instruct": 0.792,
+        "mistral-large-instruct-2411": 0.8960000000000001,
+        "gemma-2-27b-it": 0.512,
+        "gemma-2-9b-it": 0.33199999999999996,
+        "deepseek-v3": 0.976,
+        "deepseek-r1": 0.9640000000000001,
+        "qwq-32b": 0.984,
+        "Average": 0.6605333333333333
+    },
+    "ChessEnv": {
+        "qwen2.5-3b-instruct": 0.184,
+        "qwen2.5-7b-instruct": 0.27999999999999997,
+        "qwen2.5-14b-instruct": 0.592,
+        "qwen2.5-32b-instruct": 0.616,
+        "qwen2.5-72b-instruct": 0.5720000000000001,
+        "llama-3.1-8b-instruct": 0.188,
+        "llama-3.1-70b-instruct": 0.6639999999999999,
+        "llama-3.2-3b-instruct": 0.084,
+        "llama-3.3-70b-instruct": 0.6280000000000001,
+        "mistral-large-instruct-2411": 0.744,
+        "gemma-2-27b-it": 0.30000000000000004,
+        "gemma-2-9b-it": 0.096,
+        "deepseek-v3": 0.696,
+        "deepseek-r1": 0.6519999999999999,
+        "qwq-32b": 0.664,
+        "Average": 0.4639999999999999
+    },
+    "MythicalEnv": {
+        "qwen2.5-3b-instruct": 0.2,
+        "qwen2.5-7b-instruct": 0.336,
+        "qwen2.5-14b-instruct": 0.8039999999999999,
+        "qwen2.5-32b-instruct": 0.712,
+        "qwen2.5-72b-instruct": 0.632,
+        "llama-3.1-8b-instruct": 0.356,
+        "llama-3.1-70b-instruct": 0.54,
+        "llama-3.2-3b-instruct": 0.16,
+        "llama-3.3-70b-instruct": 0.556,
+        "mistral-large-instruct-2411": 0.728,
+        "gemma-2-27b-it": 0.54,
+        "gemma-2-9b-it": 0.404,
+        "deepseek-v3": 0.9279999999999999,
+        "deepseek-r1": 0.8959999999999999,
+        "qwq-32b": 0.876,
+        "Average": 0.5778666666666666
+    },
+    "ChemicalCompoundsEnv": {
+        "qwen2.5-3b-instruct": 0.18,
+        "qwen2.5-7b-instruct": 0.252,
+        "qwen2.5-14b-instruct": 0.40800000000000003,
+        "qwen2.5-32b-instruct": 0.30000000000000004,
+        "qwen2.5-72b-instruct": 0.28400000000000003,
+        "llama-3.1-8b-instruct": 0.148,
+        "llama-3.1-70b-instruct": 0.28,
+        "llama-3.2-3b-instruct": 0.14,
+        "llama-3.3-70b-instruct": 0.18000000000000002,
+        "mistral-large-instruct-2411": 0.43200000000000005,
+        "gemma-2-27b-it": 0.23200000000000004,
+        "gemma-2-9b-it": 0.13599999999999998,
+        "deepseek-v3": 0.46799999999999997,
+        "deepseek-r1": 0.624,
+        "qwq-32b": 0.752,
+        "Average": 0.32106666666666667
+    },
+    "ArchitecturalEnv": {
+        "qwen2.5-3b-instruct": 0.20400000000000001,
+        "qwen2.5-7b-instruct": 0.316,
+        "qwen2.5-14b-instruct": 0.72,
+        "qwen2.5-32b-instruct": 0.66,
+        "qwen2.5-72b-instruct": 0.7120000000000001,
+        "llama-3.1-8b-instruct": 0.256,
+        "llama-3.1-70b-instruct": 0.556,
+        "llama-3.2-3b-instruct": 0.132,
+        "llama-3.3-70b-instruct": 0.508,
+        "mistral-large-instruct-2411": 0.724,
+        "gemma-2-27b-it": 0.488,
+        "gemma-2-9b-it": 0.236,
+        "deepseek-v3": 0.82,
+        "deepseek-r1": 0.744,
+        "qwq-32b": 0.8240000000000001,
+        "Average": 0.5266666666666666
+    },
+    "ComputationEnv": {
+        "qwen2.5-3b-instruct": 0.152,
+        "qwen2.5-7b-instruct": 0.248,
+        "qwen2.5-14b-instruct": 0.76,
+        "qwen2.5-32b-instruct": 0.884,
+        "qwen2.5-72b-instruct": 0.8560000000000001,
+        "llama-3.1-8b-instruct": 0.32799999999999996,
+        "llama-3.1-70b-instruct": 0.788,
+        "llama-3.2-3b-instruct": 0.13999999999999999,
+        "llama-3.3-70b-instruct": 0.8560000000000001,
+        "mistral-large-instruct-2411": 0.828,
+        "gemma-2-27b-it": 0.45199999999999996,
+        "gemma-2-9b-it": 0.252,
+        "deepseek-v3": 0.96,
+        "deepseek-r1": 0.9399999999999998,
+        "qwq-32b": 0.908,
+        "Average": 0.6234666666666667
+    },
+    "MachinePartEnv": {
+        "qwen2.5-3b-instruct": 0.14,
+        "qwen2.5-7b-instruct": 0.32,
+        "qwen2.5-14b-instruct": 0.8240000000000001,
+        "qwen2.5-32b-instruct": 0.8800000000000001,
+        "qwen2.5-72b-instruct": 0.828,
+        "llama-3.1-8b-instruct": 0.376,
+        "llama-3.1-70b-instruct": 0.8200000000000001,
+        "llama-3.2-3b-instruct": 0.168,
+        "llama-3.3-70b-instruct": 0.8960000000000001,
+        "mistral-large-instruct-2411": 0.876,
+        "gemma-2-27b-it": 0.508,
+        "gemma-2-9b-it": 0.268,
+        "deepseek-v3": 0.9719999999999999,
+        "deepseek-r1": 0.952,
+        "qwq-32b": 0.916,
+        "Average": 0.6496
+    },
+    "LiteraryEnv": {
+        "qwen2.5-3b-instruct": 0.10400000000000001,
+        "qwen2.5-7b-instruct": 0.328,
+        "qwen2.5-14b-instruct": 0.8800000000000001,
+        "qwen2.5-32b-instruct": 0.9279999999999999,
+        "qwen2.5-72b-instruct": 0.9,
+        "llama-3.1-8b-instruct": 0.336,
+        "llama-3.1-70b-instruct": 0.664,
+        "llama-3.2-3b-instruct": 0.13999999999999999,
+        "llama-3.3-70b-instruct": 0.664,
+        "mistral-large-instruct-2411": 0.884,
+        "gemma-2-27b-it": 0.44399999999999995,
+        "gemma-2-9b-it": 0.13999999999999999,
+        "deepseek-v3": 0.984,
+        "deepseek-r1": 0.9119999999999999,
+        "qwq-32b": 0.968,
+        "Average": 0.6184
+    },
+    "MarineEnv": {
+        "qwen2.5-3b-instruct": 0.144,
+        "qwen2.5-7b-instruct": 0.384,
+        "qwen2.5-14b-instruct": 0.8720000000000001,
+        "qwen2.5-32b-instruct": 0.844,
+        "qwen2.5-72b-instruct": 0.8320000000000001,
+        "llama-3.1-8b-instruct": 0.308,
+        "llama-3.1-70b-instruct": 0.636,
+        "llama-3.2-3b-instruct": 0.12000000000000002,
+        "llama-3.3-70b-instruct": 0.704,
+        "mistral-large-instruct-2411": 0.7879999999999999,
+        "gemma-2-27b-it": 0.484,
+        "gemma-2-9b-it": 0.23199999999999998,
+        "deepseek-v3": 0.884,
+        "deepseek-r1": 0.9,
+        "qwq-32b": 0.8880000000000001,
+        "Average": 0.6013333333333334
+    },
+    "PhilosophyEnv": {
+        "qwen2.5-3b-instruct": 0.144,
+        "qwen2.5-7b-instruct": 0.3,
+        "qwen2.5-14b-instruct": 0.7280000000000001,
+        "qwen2.5-32b-instruct": 0.82,
+        "qwen2.5-72b-instruct": 0.8719999999999999,
+        "llama-3.1-8b-instruct": 0.32799999999999996,
+        "llama-3.1-70b-instruct": 0.764,
+        "llama-3.2-3b-instruct": 0.036000000000000004,
+        "llama-3.3-70b-instruct": 0.796,
+        "mistral-large-instruct-2411": 0.7879999999999999,
+        "gemma-2-27b-it": 0.372,
+        "gemma-2-9b-it": 0.28,
+        "deepseek-v3": 0.844,
+        "deepseek-r1": 0.78,
+        "qwq-32b": 0.8320000000000001,
+        "Average": 0.5789333333333334
+    },
+    "ArchaeologicalEnv": {
+        "qwen2.5-3b-instruct": 0.18,
+        "qwen2.5-7b-instruct": 0.38,
+        "qwen2.5-14b-instruct": 0.58,
+        "qwen2.5-32b-instruct": 0.608,
+        "qwen2.5-72b-instruct": 0.5640000000000001,
+        "llama-3.1-8b-instruct": 0.26,
+        "llama-3.1-70b-instruct": 0.608,
+        "llama-3.2-3b-instruct": 0.192,
+        "llama-3.3-70b-instruct": 0.548,
+        "mistral-large-instruct-2411": 0.64,
+        "gemma-2-27b-it": 0.476,
+        "gemma-2-9b-it": 0.30000000000000004,
+        "deepseek-v3": 0.916,
+        "deepseek-r1": 0.7040000000000001,
+        "qwq-32b": 0.7559999999999999,
+        "Average": 0.5141333333333333
+    },
+    "GemstoneEnv": {
+        "qwen2.5-3b-instruct": 0.192,
+        "qwen2.5-7b-instruct": 0.264,
+        "qwen2.5-14b-instruct": 0.492,
+        "qwen2.5-32b-instruct": 0.45599999999999996,
+        "qwen2.5-72b-instruct": 0.44000000000000006,
+        "llama-3.1-8b-instruct": 0.192,
+        "llama-3.1-70b-instruct": 0.40800000000000003,
+        "llama-3.2-3b-instruct": 0.15200000000000002,
+        "llama-3.3-70b-instruct": 0.45599999999999996,
+        "mistral-large-instruct-2411": 0.528,
+        "gemma-2-27b-it": 0.33999999999999997,
+        "gemma-2-9b-it": 0.256,
+        "deepseek-v3": 0.5680000000000001,
+        "deepseek-r1": 0.5680000000000001,
+        "qwq-32b": 0.636,
+        "Average": 0.3965333333333333
+    },
+    "MicrobiologyEnv": {
+        "qwen2.5-3b-instruct": 0.14400000000000002,
+        "qwen2.5-7b-instruct": 0.38400000000000006,
+        "qwen2.5-14b-instruct": 0.752,
+        "qwen2.5-32b-instruct": 0.7,
+        "qwen2.5-72b-instruct": 0.844,
+        "llama-3.1-8b-instruct": 0.316,
+        "llama-3.1-70b-instruct": 0.512,
+        "llama-3.2-3b-instruct": 0.12000000000000002,
+        "llama-3.3-70b-instruct": 0.496,
+        "mistral-large-instruct-2411": 0.764,
+        "gemma-2-27b-it": 0.504,
+        "gemma-2-9b-it": 0.172,
+        "deepseek-v3": 0.9279999999999999,
+        "deepseek-r1": 0.952,
+        "qwq-32b": 0.932,
+        "Average": 0.568
+    },
+    "SciFiEnv": {
+        "qwen2.5-3b-instruct": 0.192,
+        "qwen2.5-7b-instruct": 0.384,
+        "qwen2.5-14b-instruct": 0.7879999999999999,
+        "qwen2.5-32b-instruct": 0.776,
+        "qwen2.5-72b-instruct": 0.7879999999999999,
+        "llama-3.1-8b-instruct": 0.35200000000000004,
+        "llama-3.1-70b-instruct": 0.664,
+        "llama-3.2-3b-instruct": 0.164,
+        "llama-3.3-70b-instruct": 0.588,
+        "mistral-large-instruct-2411": 0.736,
+        "gemma-2-27b-it": 0.52,
+        "gemma-2-9b-it": 0.33599999999999997,
+        "deepseek-v3": 0.9279999999999999,
+        "deepseek-r1": 0.9199999999999999,
+        "qwq-32b": 0.9,
+        "Average": 0.6023999999999999
+    },
+    "HormoneEnv": {
+        "qwen2.5-3b-instruct": 0.152,
+        "qwen2.5-7b-instruct": 0.40800000000000003,
+        "qwen2.5-14b-instruct": 0.7999999999999999,
+        "qwen2.5-32b-instruct": 0.784,
+        "qwen2.5-72b-instruct": 0.764,
+        "llama-3.1-8b-instruct": 0.336,
+        "llama-3.1-70b-instruct": 0.76,
+        "llama-3.2-3b-instruct": 0.184,
+        "llama-3.3-70b-instruct": 0.8480000000000001,
+        "mistral-large-instruct-2411": 0.8,
+        "gemma-2-27b-it": 0.524,
+        "gemma-2-9b-it": 0.312,
+        "deepseek-v3": 0.9480000000000001,
+        "deepseek-r1": 0.944,
+        "qwq-32b": 0.852,
+        "Average": 0.6277333333333334
+    },
+    "SculptorEnv": {
+        "qwen2.5-3b-instruct": 0.23200000000000004,
+        "qwen2.5-7b-instruct": 0.4159999999999999,
+        "qwen2.5-14b-instruct": 0.7079999999999999,
+        "qwen2.5-32b-instruct": 0.636,
+        "qwen2.5-72b-instruct": 0.6,
+        "llama-3.1-8b-instruct": 0.22799999999999998,
+        "llama-3.1-70b-instruct": 0.484,
+        "llama-3.2-3b-instruct": 0.188,
+        "llama-3.3-70b-instruct": 0.532,
+        "mistral-large-instruct-2411": 0.684,
+        "gemma-2-27b-it": 0.30000000000000004,
+        "gemma-2-9b-it": 0.156,
+        "deepseek-v3": 0.788,
+        "deepseek-r1": 0.7479999999999999,
+        "qwq-32b": 0.8119999999999999,
+        "Average": 0.5008
+    },
+    "NeuroEnv": {
+        "qwen2.5-3b-instruct": 0.10800000000000001,
+        "qwen2.5-7b-instruct": 0.24400000000000005,
+        "qwen2.5-14b-instruct": 0.8960000000000001,
+        "qwen2.5-32b-instruct": 0.892,
+        "qwen2.5-72b-instruct": 0.8879999999999999,
+        "llama-3.1-8b-instruct": 0.512,
+        "llama-3.1-70b-instruct": 0.8880000000000001,
+        "llama-3.2-3b-instruct": 0.20400000000000001,
+        "llama-3.3-70b-instruct": 0.9279999999999999,
+        "mistral-large-instruct-2411": 0.8880000000000001,
+        "gemma-2-27b-it": 0.72,
+        "gemma-2-9b-it": 0.42800000000000005,
+        "deepseek-v3": 0.952,
+        "deepseek-r1": 0.932,
+        "qwq-32b": 0.852,
+        "Average": 0.6888000000000001
+    },
+    "OceanEnv": {
+        "qwen2.5-3b-instruct": 0.2,
+        "qwen2.5-7b-instruct": 0.45999999999999996,
+        "qwen2.5-14b-instruct": 0.6160000000000001,
+        "qwen2.5-32b-instruct": 0.6000000000000001,
+        "qwen2.5-72b-instruct": 0.62,
+        "llama-3.1-8b-instruct": 0.36400000000000005,
+        "llama-3.1-70b-instruct": 0.5680000000000001,
+        "llama-3.2-3b-instruct": 0.156,
+        "llama-3.3-70b-instruct": 0.476,
+        "mistral-large-instruct-2411": 0.656,
+        "gemma-2-27b-it": 0.43200000000000005,
+        "gemma-2-9b-it": 0.248,
+        "deepseek-v3": 0.852,
+        "deepseek-r1": 0.836,
+        "qwq-32b": 0.8240000000000001,
+        "Average": 0.5272000000000001
+    },
+    "MineralEnv": {
+        "qwen2.5-3b-instruct": 0.14400000000000002,
+        "qwen2.5-7b-instruct": 0.38,
+        "qwen2.5-14b-instruct": 0.768,
+        "qwen2.5-32b-instruct": 0.6960000000000001,
+        "qwen2.5-72b-instruct": 0.684,
+        "llama-3.1-8b-instruct": 0.29600000000000004,
+        "llama-3.1-70b-instruct": 0.556,
+        "llama-3.2-3b-instruct": 0.16,
+        "llama-3.3-70b-instruct": 0.56,
+        "mistral-large-instruct-2411": 0.66,
+        "gemma-2-27b-it": 0.384,
+        "gemma-2-9b-it": 0.17200000000000001,
+        "deepseek-v3": 0.8480000000000001,
+        "deepseek-r1": 0.82,
+        "qwq-32b": 0.8720000000000001,
+        "Average": 0.5333333333333333
+    },
+    "FishEnv": {
+        "qwen2.5-3b-instruct": 0.188,
+        "qwen2.5-7b-instruct": 0.38,
+        "qwen2.5-14b-instruct": 0.732,
+        "qwen2.5-32b-instruct": 0.668,
+        "qwen2.5-72b-instruct": 0.7200000000000001,
+        "llama-3.1-8b-instruct": 0.392,
+        "llama-3.1-70b-instruct": 0.624,
+        "llama-3.2-3b-instruct": 0.13599999999999998,
+        "llama-3.3-70b-instruct": 0.616,
+        "mistral-large-instruct-2411": 0.736,
+        "gemma-2-27b-it": 0.508,
+        "gemma-2-9b-it": 0.268,
+        "deepseek-v3": 0.86,
+        "deepseek-r1": 0.868,
+        "qwq-32b": 0.924,
+        "Average": 0.5746666666666667
+    },
+    "MartialArtsEnv": {
+        "qwen2.5-3b-instruct": 0.184,
+        "qwen2.5-7b-instruct": 0.43200000000000005,
+        "qwen2.5-14b-instruct": 0.672,
+        "qwen2.5-32b-instruct": 0.5640000000000001,
+        "qwen2.5-72b-instruct": 0.56,
+        "llama-3.1-8b-instruct": 0.276,
+        "llama-3.1-70b-instruct": 0.54,
+        "llama-3.2-3b-instruct": 0.2,
+        "llama-3.3-70b-instruct": 0.52,
+        "mistral-large-instruct-2411": 0.568,
+        "gemma-2-27b-it": 0.4,
+        "gemma-2-9b-it": 0.22400000000000003,
+        "deepseek-v3": 0.784,
+        "deepseek-r1": 0.716,
+        "qwq-32b": 0.752,
+        "Average": 0.4928
+    },
+    "RocketFuelEnv": {
+        "qwen2.5-3b-instruct": 0.22800000000000004,
+        "qwen2.5-7b-instruct": 0.41600000000000004,
+        "qwen2.5-14b-instruct": 0.852,
+        "qwen2.5-32b-instruct": 0.7879999999999999,
+        "qwen2.5-72b-instruct": 0.8160000000000001,
+        "llama-3.1-8b-instruct": 0.36,
+        "llama-3.1-70b-instruct": 0.6799999999999999,
+        "llama-3.2-3b-instruct": 0.184,
+        "llama-3.3-70b-instruct": 0.7239999999999999,
+        "mistral-large-instruct-2411": 0.828,
+        "gemma-2-27b-it": 0.6279999999999999,
+        "gemma-2-9b-it": 0.248,
+        "deepseek-v3": 0.916,
+        "deepseek-r1": 0.8960000000000001,
+        "qwq-32b": 0.9040000000000001,
+        "Average": 0.6312000000000001
+    },
+    "MLEnv": {
+        "qwen2.5-3b-instruct": 0.088,
+        "qwen2.5-7b-instruct": 0.392,
+        "qwen2.5-14b-instruct": 0.6,
+        "qwen2.5-32b-instruct": 0.748,
+        "qwen2.5-72b-instruct": 0.792,
+        "llama-3.1-8b-instruct": 0.304,
+        "llama-3.1-70b-instruct": 0.672,
+        "llama-3.2-3b-instruct": 0.10799999999999998,
+        "llama-3.3-70b-instruct": 0.5960000000000001,
+        "mistral-large-instruct-2411": 0.7639999999999999,
+        "gemma-2-27b-it": 0.264,
+        "gemma-2-9b-it": 0.156,
+        "deepseek-v3": 0.808,
+        "deepseek-r1": 0.652,
+        "qwq-32b": 0.772,
+        "Average": 0.5144
+    },
+    "PoliticalManifestoEnv": {
+        "qwen2.5-3b-instruct": 0.184,
+        "qwen2.5-7b-instruct": 0.312,
+        "qwen2.5-14b-instruct": 0.76,
+        "qwen2.5-32b-instruct": 0.852,
+        "qwen2.5-72b-instruct": 0.7839999999999999,
+        "llama-3.1-8b-instruct": 0.42400000000000004,
+        "llama-3.1-70b-instruct": 0.62,
+        "llama-3.2-3b-instruct": 0.128,
+        "llama-3.3-70b-instruct": 0.692,
+        "mistral-large-instruct-2411": 0.796,
+        "gemma-2-27b-it": 0.45200000000000007,
+        "gemma-2-9b-it": 0.152,
+        "deepseek-v3": 0.86,
+        "deepseek-r1": 0.792,
+        "qwq-32b": 0.8800000000000001,
+        "Average": 0.5792
+    },
+    "CoffeeEnv": {
+        "qwen2.5-3b-instruct": 0.20400000000000001,
+        "qwen2.5-7b-instruct": 0.38,
+        "qwen2.5-14b-instruct": 0.7799999999999999,
+        "qwen2.5-32b-instruct": 0.8039999999999999,
+        "qwen2.5-72b-instruct": 0.764,
+        "llama-3.1-8b-instruct": 0.31599999999999995,
+        "llama-3.1-70b-instruct": 0.552,
+        "llama-3.2-3b-instruct": 0.17200000000000001,
+        "llama-3.3-70b-instruct": 0.6599999999999999,
+        "mistral-large-instruct-2411": 0.828,
+        "gemma-2-27b-it": 0.592,
+        "gemma-2-9b-it": 0.364,
+        "deepseek-v3": 0.9120000000000001,
+        "deepseek-r1": 0.9279999999999999,
+        "qwq-32b": 0.9359999999999999,
+        "Average": 0.6128
+    },
+    "MotifAnalysisEnv": {
+        "qwen2.5-3b-instruct": 0.096,
+        "qwen2.5-7b-instruct": 0.332,
+        "qwen2.5-14b-instruct": 0.5680000000000001,
+        "qwen2.5-32b-instruct": 0.496,
+        "qwen2.5-72b-instruct": 0.5920000000000001,
+        "llama-3.1-8b-instruct": 0.244,
+        "llama-3.1-70b-instruct": 0.36000000000000004,
+        "llama-3.2-3b-instruct": 0.13999999999999999,
+        "llama-3.3-70b-instruct": 0.22400000000000003,
+        "mistral-large-instruct-2411": 0.46399999999999997,
+        "gemma-2-27b-it": 0.18,
+        "gemma-2-9b-it": 0.128,
+        "deepseek-v3": 0.752,
+        "deepseek-r1": 0.8240000000000001,
+        "qwq-32b": 0.8640000000000001,
+        "Average": 0.4176
+    },
+    "NutritionEnv": {
+        "qwen2.5-3b-instruct": 0.132,
+        "qwen2.5-7b-instruct": 0.22000000000000003,
+        "qwen2.5-14b-instruct": 0.7920000000000001,
+        "qwen2.5-32b-instruct": 0.8400000000000001,
+        "qwen2.5-72b-instruct": 0.876,
+        "llama-3.1-8b-instruct": 0.264,
+        "llama-3.1-70b-instruct": 0.64,
+        "llama-3.2-3b-instruct": 0.128,
+        "llama-3.3-70b-instruct": 0.7040000000000001,
+        "mistral-large-instruct-2411": 0.8320000000000001,
+        "gemma-2-27b-it": 0.38,
+        "gemma-2-9b-it": 0.20800000000000002,
+        "deepseek-v3": 0.944,
+        "deepseek-r1": 0.944,
+        "qwq-32b": 0.9120000000000001,
+        "Average": 0.5877333333333333
+    },
+    "MalwareEnv": {
+        "qwen2.5-3b-instruct": 0.16,
+        "qwen2.5-7b-instruct": 0.316,
+        "qwen2.5-14b-instruct": 0.728,
+        "qwen2.5-32b-instruct": 0.756,
+        "qwen2.5-72b-instruct": 0.7200000000000001,
+        "llama-3.1-8b-instruct": 0.268,
+        "llama-3.1-70b-instruct": 0.5840000000000001,
+        "llama-3.2-3b-instruct": 0.10800000000000001,
+        "llama-3.3-70b-instruct": 0.548,
+        "mistral-large-instruct-2411": 0.752,
+        "gemma-2-27b-it": 0.252,
+        "gemma-2-9b-it": 0.12,
+        "deepseek-v3": 0.916,
+        "deepseek-r1": 0.9,
+        "qwq-32b": 0.916,
+        "Average": 0.5362666666666667
+    },
+    "GeologicalEnv": {
+        "qwen2.5-3b-instruct": 0.132,
+        "qwen2.5-7b-instruct": 0.336,
+        "qwen2.5-14b-instruct": 0.7639999999999999,
+        "qwen2.5-32b-instruct": 0.748,
+        "qwen2.5-72b-instruct": 0.676,
+        "llama-3.1-8b-instruct": 0.28800000000000003,
+        "llama-3.1-70b-instruct": 0.552,
+        "llama-3.2-3b-instruct": 0.13999999999999999,
+        "llama-3.3-70b-instruct": 0.508,
+        "mistral-large-instruct-2411": 0.812,
+        "gemma-2-27b-it": 0.41600000000000004,
+        "gemma-2-9b-it": 0.164,
+        "deepseek-v3": 0.9119999999999999,
+        "deepseek-r1": 0.8480000000000001,
+        "qwq-32b": 0.8880000000000001,
+        "Average": 0.5456000000000001
+    },
+    "TheatricalEnv": {
+        "qwen2.5-3b-instruct": 0.14400000000000002,
+        "qwen2.5-7b-instruct": 0.42400000000000004,
+        "qwen2.5-14b-instruct": 0.676,
+        "qwen2.5-32b-instruct": 0.78,
+        "qwen2.5-72b-instruct": 0.808,
+        "llama-3.1-8b-instruct": 0.41200000000000003,
+        "llama-3.1-70b-instruct": 0.7959999999999999,
+        "llama-3.2-3b-instruct": 0.1,
+        "llama-3.3-70b-instruct": 0.768,
+        "mistral-large-instruct-2411": 0.844,
+        "gemma-2-27b-it": 0.528,
+        "gemma-2-9b-it": 0.28,
+        "deepseek-v3": 0.884,
+        "deepseek-r1": 0.8240000000000001,
+        "qwq-32b": 0.908,
+        "Average": 0.6117333333333335
+    },
+    "PrintingTechniqueEnv": {
+        "qwen2.5-3b-instruct": 0.144,
+        "qwen2.5-7b-instruct": 0.252,
+        "qwen2.5-14b-instruct": 0.736,
+        "qwen2.5-32b-instruct": 0.7200000000000001,
+        "qwen2.5-72b-instruct": 0.776,
+        "llama-3.1-8b-instruct": 0.4,
+        "llama-3.1-70b-instruct": 0.54,
+        "llama-3.2-3b-instruct": 0.16,
+        "llama-3.3-70b-instruct": 0.548,
+        "mistral-large-instruct-2411": 0.7040000000000001,
+        "gemma-2-27b-it": 0.44000000000000006,
+        "gemma-2-9b-it": 0.192,
+        "deepseek-v3": 0.916,
+        "deepseek-r1": 0.852,
+        "qwq-32b": 0.9279999999999999,
+        "Average": 0.5538666666666666
+    },
+    "StellarEnv": {
+        "qwen2.5-3b-instruct": 0.132,
+        "qwen2.5-7b-instruct": 0.388,
+        "qwen2.5-14b-instruct": 0.6759999999999999,
+        "qwen2.5-32b-instruct": 0.724,
+        "qwen2.5-72b-instruct": 0.6960000000000001,
+        "llama-3.1-8b-instruct": 0.30000000000000004,
+        "llama-3.1-70b-instruct": 0.6040000000000001,
+        "llama-3.2-3b-instruct": 0.16,
+        "llama-3.3-70b-instruct": 0.6240000000000001,
+        "mistral-large-instruct-2411": 0.732,
+        "gemma-2-27b-it": 0.364,
+        "gemma-2-9b-it": 0.23199999999999998,
+        "deepseek-v3": 0.82,
+        "deepseek-r1": 0.648,
+        "qwq-32b": 0.776,
+        "Average": 0.5250666666666667
+    },
+    "SoilEnv": {
+        "qwen2.5-3b-instruct": 0.172,
+        "qwen2.5-7b-instruct": 0.48,
+        "qwen2.5-14b-instruct": 0.8320000000000001,
+        "qwen2.5-32b-instruct": 0.788,
+        "qwen2.5-72b-instruct": 0.8240000000000001,
+        "llama-3.1-8b-instruct": 0.42400000000000004,
+        "llama-3.1-70b-instruct": 0.64,
+        "llama-3.2-3b-instruct": 0.22799999999999998,
+        "llama-3.3-70b-instruct": 0.664,
+        "mistral-large-instruct-2411": 0.76,
+        "gemma-2-27b-it": 0.628,
+        "gemma-2-9b-it": 0.44000000000000006,
+        "deepseek-v3": 0.884,
+        "deepseek-r1": 0.8039999999999999,
+        "qwq-32b": 0.8480000000000001,
+        "Average": 0.6277333333333334
+    },
+    "SoftwareEnv": {
+        "qwen2.5-3b-instruct": 0.14800000000000002,
+        "qwen2.5-7b-instruct": 0.40800000000000003,
+        "qwen2.5-14b-instruct": 0.744,
+        "qwen2.5-32b-instruct": 0.86,
+        "qwen2.5-72b-instruct": 0.8400000000000001,
+        "llama-3.1-8b-instruct": 0.4159999999999999,
+        "llama-3.1-70b-instruct": 0.72,
+        "llama-3.2-3b-instruct": 0.16799999999999998,
+        "llama-3.3-70b-instruct": 0.784,
+        "mistral-large-instruct-2411": 0.804,
+        "gemma-2-27b-it": 0.528,
+        "gemma-2-9b-it": 0.308,
+        "deepseek-v3": 0.836,
+        "deepseek-r1": 0.8360000000000001,
+        "qwq-32b": 0.8800000000000001,
+        "Average": 0.6186666666666667
+    },
+    "CarIdentificationEnv": {
+        "qwen2.5-3b-instruct": 0.272,
+        "qwen2.5-7b-instruct": 0.4,
+        "qwen2.5-14b-instruct": 0.9120000000000001,
+        "qwen2.5-32b-instruct": 0.916,
+        "qwen2.5-72b-instruct": 0.9359999999999999,
+        "llama-3.1-8b-instruct": 0.544,
+        "llama-3.1-70b-instruct": 0.8400000000000001,
+        "llama-3.2-3b-instruct": 0.124,
+        "llama-3.3-70b-instruct": 0.852,
+        "mistral-large-instruct-2411": 0.9119999999999999,
+        "gemma-2-27b-it": 0.672,
+        "gemma-2-9b-it": 0.376,
+        "deepseek-v3": 0.992,
+        "deepseek-r1": 0.952,
+        "qwq-32b": 0.9879999999999999,
+        "Average": 0.7125333333333334
+    },
+    "PharmaceuticalEnv": {
+        "qwen2.5-3b-instruct": 0.156,
+        "qwen2.5-7b-instruct": 0.32,
+        "qwen2.5-14b-instruct": 0.7600000000000001,
+        "qwen2.5-32b-instruct": 0.752,
+        "qwen2.5-72b-instruct": 0.7559999999999999,
+        "llama-3.1-8b-instruct": 0.28400000000000003,
+        "llama-3.1-70b-instruct": 0.508,
+        "llama-3.2-3b-instruct": 0.148,
+        "llama-3.3-70b-instruct": 0.472,
+        "mistral-large-instruct-2411": 0.756,
+        "gemma-2-27b-it": 0.336,
+        "gemma-2-9b-it": 0.128,
+        "deepseek-v3": 0.8800000000000001,
+        "deepseek-r1": 0.8640000000000001,
+        "qwq-32b": 0.8,
+        "Average": 0.528
+    },
+    "NetworkEnv": {
+        "qwen2.5-3b-instruct": 0.184,
+        "qwen2.5-7b-instruct": 0.36,
+        "qwen2.5-14b-instruct": 0.66,
+        "qwen2.5-32b-instruct": 0.716,
+        "qwen2.5-72b-instruct": 0.716,
+        "llama-3.1-8b-instruct": 0.43199999999999994,
+        "llama-3.1-70b-instruct": 0.68,
+        "llama-3.2-3b-instruct": 0.14400000000000002,
+        "llama-3.3-70b-instruct": 0.7040000000000001,
+        "mistral-large-instruct-2411": 0.78,
+        "gemma-2-27b-it": 0.492,
+        "gemma-2-9b-it": 0.392,
+        "deepseek-v3": 0.8400000000000001,
+        "deepseek-r1": 0.736,
+        "qwq-32b": 0.828,
+        "Average": 0.5776
+    },
+    "BirdNestEnv": {
+        "qwen2.5-3b-instruct": 0.148,
+        "qwen2.5-7b-instruct": 0.21200000000000002,
+        "qwen2.5-14b-instruct": 0.48,
+        "qwen2.5-32b-instruct": 0.33999999999999997,
+        "qwen2.5-72b-instruct": 0.42400000000000004,
+        "llama-3.1-8b-instruct": 0.16799999999999998,
+        "llama-3.1-70b-instruct": 0.22400000000000003,
+        "llama-3.2-3b-instruct": 0.084,
+        "llama-3.3-70b-instruct": 0.20800000000000002,
+        "mistral-large-instruct-2411": 0.492,
+        "gemma-2-27b-it": 0.176,
+        "gemma-2-9b-it": 0.128,
+        "deepseek-v3": 0.764,
+        "deepseek-r1": 0.756,
+        "qwq-32b": 0.8119999999999999,
+        "Average": 0.36106666666666676
+    },
+    "EnergyEnv": {
+        "qwen2.5-3b-instruct": 0.15999999999999998,
+        "qwen2.5-7b-instruct": 0.42000000000000004,
+        "qwen2.5-14b-instruct": 0.7999999999999999,
+        "qwen2.5-32b-instruct": 0.7,
+        "qwen2.5-72b-instruct": 0.5880000000000001,
+        "llama-3.1-8b-instruct": 0.29600000000000004,
+        "llama-3.1-70b-instruct": 0.46799999999999997,
+        "llama-3.2-3b-instruct": 0.18,
+        "llama-3.3-70b-instruct": 0.396,
+        "mistral-large-instruct-2411": 0.78,
+        "gemma-2-27b-it": 0.35200000000000004,
+        "gemma-2-9b-it": 0.196,
+        "deepseek-v3": 0.916,
+        "deepseek-r1": 0.8720000000000001,
+        "qwq-32b": 0.8880000000000001,
+        "Average": 0.5341333333333333
+    },
+    "LanguageEnv": {
+        "qwen2.5-3b-instruct": 0.196,
+        "qwen2.5-7b-instruct": 0.304,
+        "qwen2.5-14b-instruct": 0.388,
+        "qwen2.5-32b-instruct": 0.512,
+        "qwen2.5-72b-instruct": 0.5599999999999999,
+        "llama-3.1-8b-instruct": 0.23200000000000004,
+        "llama-3.1-70b-instruct": 0.40800000000000003,
+        "llama-3.2-3b-instruct": 0.144,
+        "llama-3.3-70b-instruct": 0.336,
+        "mistral-large-instruct-2411": 0.536,
+        "gemma-2-27b-it": 0.20800000000000002,
+        "gemma-2-9b-it": 0.172,
+        "deepseek-v3": 0.724,
+        "deepseek-r1": 0.716,
+        "qwq-32b": 0.8119999999999999,
+        "Average": 0.41653333333333337
+    },
+    "AlgorithmEnv": {
+        "qwen2.5-3b-instruct": 0.1,
+        "qwen2.5-7b-instruct": 0.28400000000000003,
+        "qwen2.5-14b-instruct": 0.688,
+        "qwen2.5-32b-instruct": 0.6960000000000001,
+        "qwen2.5-72b-instruct": 0.66,
+        "llama-3.1-8b-instruct": 0.35200000000000004,
+        "llama-3.1-70b-instruct": 0.512,
+        "llama-3.2-3b-instruct": 0.22399999999999998,
+        "llama-3.3-70b-instruct": 0.484,
+        "mistral-large-instruct-2411": 0.788,
+        "gemma-2-27b-it": 0.268,
+        "gemma-2-9b-it": 0.164,
+        "deepseek-v3": 0.792,
+        "deepseek-r1": 0.724,
+        "qwq-32b": 0.812,
+        "Average": 0.5032
+    },
+    "MathematicalEnv": {
+        "qwen2.5-3b-instruct": 0.048,
+        "qwen2.5-7b-instruct": 0.42800000000000005,
+        "qwen2.5-14b-instruct": 0.7000000000000001,
+        "qwen2.5-32b-instruct": 0.8119999999999999,
+        "qwen2.5-72b-instruct": 0.792,
+        "llama-3.1-8b-instruct": 0.316,
+        "llama-3.1-70b-instruct": 0.8,
+        "llama-3.2-3b-instruct": 0.12800000000000003,
+        "llama-3.3-70b-instruct": 0.8400000000000001,
+        "mistral-large-instruct-2411": 0.884,
+        "gemma-2-27b-it": 0.268,
+        "gemma-2-9b-it": 0.068,
+        "deepseek-v3": 0.9119999999999999,
+        "deepseek-r1": 0.876,
+        "qwq-32b": 0.8160000000000001,
+        "Average": 0.5792
+    },
+    "MusicalEnv": {
+        "qwen2.5-3b-instruct": 0.04,
+        "qwen2.5-7b-instruct": 0.336,
+        "qwen2.5-14b-instruct": 0.8039999999999999,
+        "qwen2.5-32b-instruct": 0.8560000000000001,
+        "qwen2.5-72b-instruct": 0.8400000000000001,
+        "llama-3.1-8b-instruct": 0.34400000000000003,
+        "llama-3.1-70b-instruct": 0.68,
+        "llama-3.2-3b-instruct": 0.088,
+        "llama-3.3-70b-instruct": 0.8240000000000001,
+        "mistral-large-instruct-2411": 0.884,
+        "gemma-2-27b-it": 0.28,
+        "gemma-2-9b-it": 0.11599999999999999,
+        "deepseek-v3": 0.9480000000000001,
+        "deepseek-r1": 0.892,
+        "qwq-32b": 0.9039999999999999,
+        "Average": 0.5890666666666668
+    },
+    "InventorEnv": {
+        "qwen2.5-3b-instruct": 0.14800000000000002,
+        "qwen2.5-7b-instruct": 0.43200000000000005,
+        "qwen2.5-14b-instruct": 0.776,
+        "qwen2.5-32b-instruct": 0.7999999999999999,
+        "qwen2.5-72b-instruct": 0.772,
+        "llama-3.1-8b-instruct": 0.4,
+        "llama-3.1-70b-instruct": 0.7,
+        "llama-3.2-3b-instruct": 0.188,
+        "llama-3.3-70b-instruct": 0.616,
+        "mistral-large-instruct-2411": 0.8039999999999999,
+        "gemma-2-27b-it": 0.552,
+        "gemma-2-9b-it": 0.364,
+        "deepseek-v3": 0.9399999999999998,
+        "deepseek-r1": 0.908,
+        "qwq-32b": 0.9,
+        "Average": 0.62
+    },
+    "MedicalEnv": {
+        "qwen2.5-3b-instruct": 0.22000000000000003,
+        "qwen2.5-7b-instruct": 0.544,
+        "qwen2.5-14b-instruct": 0.8320000000000001,
+        "qwen2.5-32b-instruct": 0.8800000000000001,
+        "qwen2.5-72b-instruct": 0.8960000000000001,
+        "llama-3.1-8b-instruct": 0.52,
+        "llama-3.1-70b-instruct": 0.82,
+        "llama-3.2-3b-instruct": 0.23200000000000004,
+        "llama-3.3-70b-instruct": 0.8960000000000001,
+        "mistral-large-instruct-2411": 0.8960000000000001,
+        "gemma-2-27b-it": 0.692,
+        "gemma-2-9b-it": 0.5760000000000001,
+        "deepseek-v3": 0.9039999999999999,
+        "deepseek-r1": 0.9359999999999999,
+        "qwq-32b": 0.9199999999999999,
+        "Average": 0.7175999999999999
+    },
+    "MusicEnv": {
+        "qwen2.5-3b-instruct": 0.184,
+        "qwen2.5-7b-instruct": 0.26,
+        "qwen2.5-14b-instruct": 0.656,
+        "qwen2.5-32b-instruct": 0.664,
+        "qwen2.5-72b-instruct": 0.7559999999999999,
+        "llama-3.1-8b-instruct": 0.356,
+        "llama-3.1-70b-instruct": 0.596,
+        "llama-3.2-3b-instruct": 0.10800000000000001,
+        "llama-3.3-70b-instruct": 0.596,
+        "mistral-large-instruct-2411": 0.6639999999999999,
+        "gemma-2-27b-it": 0.45600000000000007,
+        "gemma-2-9b-it": 0.28400000000000003,
+        "deepseek-v3": 0.8119999999999999,
+        "deepseek-r1": 0.868,
+        "qwq-32b": 0.868,
+        "Average": 0.5418666666666667
+    },
+    "FantasyEnv": {
+        "qwen2.5-3b-instruct": 0.148,
+        "qwen2.5-7b-instruct": 0.32,
+        "qwen2.5-14b-instruct": 0.74,
+        "qwen2.5-32b-instruct": 0.7879999999999999,
+        "qwen2.5-72b-instruct": 0.5720000000000001,
+        "llama-3.1-8b-instruct": 0.40800000000000003,
+        "llama-3.1-70b-instruct": 0.676,
+        "llama-3.2-3b-instruct": 0.152,
+        "llama-3.3-70b-instruct": 0.704,
+        "mistral-large-instruct-2411": 0.8240000000000001,
+        "gemma-2-27b-it": 0.524,
+        "gemma-2-9b-it": 0.324,
+        "deepseek-v3": 0.9199999999999999,
+        "deepseek-r1": 0.9719999999999999,
+        "qwq-32b": 0.9719999999999999,
+        "Average": 0.6029333333333332
+    },
+    "EducationEnv": {
+        "qwen2.5-3b-instruct": 0.10400000000000001,
+        "qwen2.5-7b-instruct": 0.268,
+        "qwen2.5-14b-instruct": 0.828,
+        "qwen2.5-32b-instruct": 0.9039999999999999,
+        "qwen2.5-72b-instruct": 0.8480000000000001,
+        "llama-3.1-8b-instruct": 0.5680000000000001,
+        "llama-3.1-70b-instruct": 0.768,
+        "llama-3.2-3b-instruct": 0.192,
+        "llama-3.3-70b-instruct": 0.9039999999999999,
+        "mistral-large-instruct-2411": 0.876,
+        "gemma-2-27b-it": 0.624,
+        "gemma-2-9b-it": 0.45999999999999996,
+        "deepseek-v3": 0.9480000000000001,
+        "deepseek-r1": 0.9,
+        "qwq-32b": 0.9359999999999999,
+        "Average": 0.6752
+    },
+    "ChemicalEnv": {
+        "qwen2.5-3b-instruct": 0.264,
+        "qwen2.5-7b-instruct": 0.44000000000000006,
+        "qwen2.5-14b-instruct": 0.724,
+        "qwen2.5-32b-instruct": 0.7040000000000001,
+        "qwen2.5-72b-instruct": 0.72,
+        "llama-3.1-8b-instruct": 0.36,
+        "llama-3.1-70b-instruct": 0.62,
+        "llama-3.2-3b-instruct": 0.16399999999999998,
+        "llama-3.3-70b-instruct": 0.45999999999999996,
+        "mistral-large-instruct-2411": 0.68,
+        "gemma-2-27b-it": 0.44399999999999995,
+        "gemma-2-9b-it": 0.316,
+        "deepseek-v3": 0.8799999999999999,
+        "deepseek-r1": 0.6799999999999999,
+        "qwq-32b": 0.8200000000000001,
+        "Average": 0.5517333333333333
+    },
+    "Average": {
+        "qwen2.5-3b-instruct": 0.1655841584158416,
+        "qwen2.5-7b-instruct": 0.34736633663366323,
+        "qwen2.5-14b-instruct": 0.7148514851485149,
+        "qwen2.5-32b-instruct": 0.7330693069306928,
+        "qwen2.5-72b-instruct": 0.7272079207920793,
+        "llama-3.1-8b-instruct": 0.3334653465346535,
+        "llama-3.1-70b-instruct": 0.6271287128712871,
+        "llama-3.2-3b-instruct": 0.15599999999999997,
+        "llama-3.3-70b-instruct": 0.6372277227722771,
+        "mistral-large-instruct-2411": 0.7573861386138615,
+        "gemma-2-27b-it": 0.44522772277227735,
+        "gemma-2-9b-it": 0.264,
+        "deepseek-v3": 0.8605148514851484,
+        "deepseek-r1": 0.8304554455445546,
+        "qwq-32b": 0.8630891089108911
+    }
+}

src/display/css_html_js.py → display.py

@@ -1,34 +1,26 @@
 custom_css = """
-
 .markdown-text {
     font-size: 16px !important;
 }
-
 #models-to-add-text {
     font-size: 18px !important;
 }
-
 #citation-button span {
     font-size: 16px !important;
 }
-
 #citation-button textarea {
     font-size: 16px !important;
 }
-
 #citation-button > label > button {
     margin: 6px;
     transform: scale(1.3);
 }
-
 #leaderboard-table {
     margin-top: 15px
 }
-
 #leaderboard-table-lite {
     margin-top: 15px
 }
-
 #search-bar-table-box > div:first-child {
     background: none;
     border: none;
@@ -37,7 +29,6 @@ custom_css = """
 #search-bar {
     padding: 0px;
 }
-
 /* Limit the width of the first AutoEvalColumn so that names don't expand too much */
 #leaderboard-table td:nth-child(2),
 #leaderboard-table th:nth-child(2) {
@@ -45,11 +36,9 @@ custom_css = """
     overflow: auto;
     white-space: nowrap;
 }
-
 .tab-buttons button {
     font-size: 20px;
 }
-
 #scale-logo {
     border-style: none !important;
     box-shadow: none;
@@ -58,7 +47,6 @@ custom_css = """
     margin-right: auto;
     max-width: 600px;
 }
-
 #scale-logo .download {
     display: none;
 }
@@ -102,4 +90,4 @@ get_window_url_params = """
         url_params = Object.fromEntries(params);
         return url_params;
     }
-    """
+    """

process_data.py

@@ -0,0 +1,47 @@
+import pandas as pd
+import json
+
+hard_data_path = 'data/hard_0402.json'
+easy_data_path = 'data/easy_0402.json'
+
+average_success_rate_file_path = 'data/success_rate_0402.json'
+average_action_count_file_path = 'data/action_count_0402.json'
+
+def load_average_data():
+    with open(average_success_rate_file_path, 'r') as f:
+        average_success_rate_data = json.load(f)
+    with open(average_action_count_file_path, 'r') as f:
+        average_action_count_data = json.load(f)
+    average_success_rate = average_success_rate_data['Average']
+    average_action_count = average_action_count_data['Average']
+    df = pd.DataFrame({
+            'Success Rate ↑ (100 Average)': average_success_rate,
+            'Action Count ↓ (100 Average)': average_action_count
+        })
+    return df
+
+def load_hard_data():
+    with open(hard_data_path, 'r') as f:
+        hard_data = json.load(f)
+    df = pd.DataFrame(hard_data)
+    df = df.T # 转置为 model 是行，指标是列
+    df.rename(columns={'success_rate':'Success Rate ↑ (Hard)', 'relative_action_count':'Action Count ↓ (Hard)'}, inplace=True)
+    return df
+
+def load_easy_data():
+    with open(easy_data_path, 'r') as f:
+        hard_data = json.load(f)
+    df = pd.DataFrame(hard_data)
+    df = df.T # 转置为 model 是行，指标是列
+    df.rename(columns={'success_rate':'Success Rate ↑ (Easy)', 'relative_action_count':'Action Count ↓ (Easy)'}, inplace=True)
+    return df
+
+
+if __name__ == '__main__':
+    average_df = load_average_data()
+    hard_df = load_hard_data()
+    easy_df = load_easy_data()
+    import ipdb; ipdb.set_trace()
+    df = pd.concat([average_df, hard_df, easy_df], axis=1)
+    print(df)
+    

pyproject.toml

@@ -1,13 +0,0 @@
-[tool.ruff]
-# Enable pycodestyle (`E`) and Pyflakes (`F`) codes by default.
-select = ["E", "F"]
-ignore = ["E501"] # line too long (black is taking care of this)
-line-length = 119
-fixable = ["A", "B", "C", "D", "E", "F", "G", "I", "N", "Q", "S", "T", "W", "ANN", "ARG", "BLE", "COM", "DJ", "DTZ", "EM", "ERA", "EXE", "FBT", "ICN", "INP", "ISC", "NPY", "PD", "PGH", "PIE", "PL", "PT", "PTH", "PYI", "RET", "RSE", "RUF", "SIM", "SLF", "TCH", "TID", "TRY", "UP", "YTT"]
-
-[tool.isort]
-profile = "black"
-line_length = 119
-
-[tool.black]
-line-length = 119

requirements.txt

@@ -1,16 +1,3 @@
-APScheduler
-black
-datasets
-gradio
-gradio[oauth]
-gradio_leaderboard==0.0.13
-gradio_client
-huggingface-hub>=0.18.0
-matplotlib
-numpy
+apscheduler
 pandas
-python-dateutil
-tqdm
-transformers
-tokenizers>=0.15.0
-sentencepiece
+datasets==2.21.0

src/about.py

@@ -1,72 +0,0 @@
-from dataclasses import dataclass
-from enum import Enum
-
-@dataclass
-class Task:
-    benchmark: str
-    metric: str
-    col_name: str
-
-
-# Select your tasks here
-# ---------------------------------------------------
-class Tasks(Enum):
-    # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
-    task0 = Task("anli_r1", "acc", "ANLI")
-    task1 = Task("logiqa", "acc_norm", "LogiQA")
-
-NUM_FEWSHOT = 0 # Change with your few shot
-# ---------------------------------------------------
-
-
-
-# Your leaderboard name
-TITLE = """<h1 align="center" id="space-title">Demo leaderboard</h1>"""
-
-# What does your leaderboard evaluate?
-INTRODUCTION_TEXT = """
-Intro text
-"""
-
-# Which evaluations are you running? how can people reproduce what you have?
-LLM_BENCHMARKS_TEXT = f"""
-## How it works
-
-## Reproducibility
-To reproduce our results, here is the commands you can run:
-
-"""
-
-EVALUATION_QUEUE_TEXT = """
-## Some good practices before submitting a model
-
-### 1) Make sure you can load your model and tokenizer using AutoClasses:
-```python
-from transformers import AutoConfig, AutoModel, AutoTokenizer
-config = AutoConfig.from_pretrained("your model name", revision=revision)
-model = AutoModel.from_pretrained("your model name", revision=revision)
-tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
-```
-If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded.
-
-Note: make sure your model is public!
-Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!
-
-### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
-It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!
-
-### 3) Make sure your model has an open license!
-This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗
-
-### 4) Fill up your model card
-When we add extra information about models to the leaderboard, it will be automatically taken from the model card
-
-## In case of model failure
-If your model is displayed in the `FAILED` category, its execution stopped.
-Make sure you have followed the above steps first.
-If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task).
-"""
-
-CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
-CITATION_BUTTON_TEXT = r"""
-"""

src/display/formatting.py

@@ -1,27 +0,0 @@
-def model_hyperlink(link, model_name):
-    return f'<a target="_blank" href="{link}" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">{model_name}</a>'
-
-
-def make_clickable_model(model_name):
-    link = f"https://huggingface.co/{model_name}"
-    return model_hyperlink(link, model_name)
-
-
-def styled_error(error):
-    return f"<p style='color: red; font-size: 20px; text-align: center;'>{error}</p>"
-
-
-def styled_warning(warn):
-    return f"<p style='color: orange; font-size: 20px; text-align: center;'>{warn}</p>"
-
-
-def styled_message(message):
-    return f"<p style='color: green; font-size: 20px; text-align: center;'>{message}</p>"
-
-
-def has_no_nan_values(df, columns):
-    return df[columns].notna().all(axis=1)
-
-
-def has_nan_values(df, columns):
-    return df[columns].isna().any(axis=1)

src/display/utils.py

@@ -1,110 +0,0 @@
-from dataclasses import dataclass, make_dataclass
-from enum import Enum
-
-import pandas as pd
-
-from src.about import Tasks
-
-def fields(raw_class):
-    return [v for k, v in raw_class.__dict__.items() if k[:2] != "__" and k[-2:] != "__"]
-
-
-# These classes are for user facing column names,
-# to avoid having to change them all around the code
-# when a modif is needed
-@dataclass
-class ColumnContent:
-    name: str
-    type: str
-    displayed_by_default: bool
-    hidden: bool = False
-    never_hidden: bool = False
-
-## Leaderboard columns
-auto_eval_column_dict = []
-# Init
-auto_eval_column_dict.append(["model_type_symbol", ColumnContent, ColumnContent("T", "str", True, never_hidden=True)])
-auto_eval_column_dict.append(["model", ColumnContent, ColumnContent("Model", "markdown", True, never_hidden=True)])
-#Scores
-auto_eval_column_dict.append(["average", ColumnContent, ColumnContent("Average ⬆️", "number", True)])
-for task in Tasks:
-    auto_eval_column_dict.append([task.name, ColumnContent, ColumnContent(task.value.col_name, "number", True)])
-# Model information
-auto_eval_column_dict.append(["model_type", ColumnContent, ColumnContent("Type", "str", False)])
-auto_eval_column_dict.append(["architecture", ColumnContent, ColumnContent("Architecture", "str", False)])
-auto_eval_column_dict.append(["weight_type", ColumnContent, ColumnContent("Weight type", "str", False, True)])
-auto_eval_column_dict.append(["precision", ColumnContent, ColumnContent("Precision", "str", False)])
-auto_eval_column_dict.append(["license", ColumnContent, ColumnContent("Hub License", "str", False)])
-auto_eval_column_dict.append(["params", ColumnContent, ColumnContent("#Params (B)", "number", False)])
-auto_eval_column_dict.append(["likes", ColumnContent, ColumnContent("Hub ❤️", "number", False)])
-auto_eval_column_dict.append(["still_on_hub", ColumnContent, ColumnContent("Available on the hub", "bool", False)])
-auto_eval_column_dict.append(["revision", ColumnContent, ColumnContent("Model sha", "str", False, False)])
-
-# We use make dataclass to dynamically fill the scores from Tasks
-AutoEvalColumn = make_dataclass("AutoEvalColumn", auto_eval_column_dict, frozen=True)
-
-## For the queue columns in the submission tab
-@dataclass(frozen=True)
-class EvalQueueColumn:  # Queue column
-    model = ColumnContent("model", "markdown", True)
-    revision = ColumnContent("revision", "str", True)
-    private = ColumnContent("private", "bool", True)
-    precision = ColumnContent("precision", "str", True)
-    weight_type = ColumnContent("weight_type", "str", "Original")
-    status = ColumnContent("status", "str", True)
-
-## All the model information that we might need
-@dataclass
-class ModelDetails:
-    name: str
-    display_name: str = ""
-    symbol: str = "" # emoji
-
-
-class ModelType(Enum):
-    PT = ModelDetails(name="pretrained", symbol="🟢")
-    FT = ModelDetails(name="fine-tuned", symbol="🔶")
-    IFT = ModelDetails(name="instruction-tuned", symbol="⭕")
-    RL = ModelDetails(name="RL-tuned", symbol="🟦")
-    Unknown = ModelDetails(name="", symbol="?")
-
-    def to_str(self, separator=" "):
-        return f"{self.value.symbol}{separator}{self.value.name}"
-
-    @staticmethod
-    def from_str(type):
-        if "fine-tuned" in type or "🔶" in type:
-            return ModelType.FT
-        if "pretrained" in type or "🟢" in type:
-            return ModelType.PT
-        if "RL-tuned" in type or "🟦" in type:
-            return ModelType.RL
-        if "instruction-tuned" in type or "⭕" in type:
-            return ModelType.IFT
-        return ModelType.Unknown
-
-class WeightType(Enum):
-    Adapter = ModelDetails("Adapter")
-    Original = ModelDetails("Original")
-    Delta = ModelDetails("Delta")
-
-class Precision(Enum):
-    float16 = ModelDetails("float16")
-    bfloat16 = ModelDetails("bfloat16")
-    Unknown = ModelDetails("?")
-
-    def from_str(precision):
-        if precision in ["torch.float16", "float16"]:
-            return Precision.float16
-        if precision in ["torch.bfloat16", "bfloat16"]:
-            return Precision.bfloat16
-        return Precision.Unknown
-
-# Column selection
-COLS = [c.name for c in fields(AutoEvalColumn) if not c.hidden]
-
-EVAL_COLS = [c.name for c in fields(EvalQueueColumn)]
-EVAL_TYPES = [c.type for c in fields(EvalQueueColumn)]
-
-BENCHMARK_COLS = [t.value.col_name for t in Tasks]
-

src/envs.py

@@ -1,25 +0,0 @@
-import os
-
-from huggingface_hub import HfApi
-
-# Info to change for your repository
-# ----------------------------------
-TOKEN = os.environ.get("HF_TOKEN") # A read/write token for your org
-
-OWNER = "demo-leaderboard-backend" # Change to your org - don't forget to create a results and request dataset, with the correct format!
-# ----------------------------------
-
-REPO_ID = f"{OWNER}/leaderboard"
-QUEUE_REPO = f"{OWNER}/requests"
-RESULTS_REPO = f"{OWNER}/results"
-
-# If you setup a cache later, just change HF_HOME
-CACHE_PATH=os.getenv("HF_HOME", ".")
-
-# Local caches
-EVAL_REQUESTS_PATH = os.path.join(CACHE_PATH, "eval-queue")
-EVAL_RESULTS_PATH = os.path.join(CACHE_PATH, "eval-results")
-EVAL_REQUESTS_PATH_BACKEND = os.path.join(CACHE_PATH, "eval-queue-bk")
-EVAL_RESULTS_PATH_BACKEND = os.path.join(CACHE_PATH, "eval-results-bk")
-
-API = HfApi(token=TOKEN)

src/leaderboard/read_evals.py

@@ -1,196 +0,0 @@
-import glob
-import json
-import math
-import os
-from dataclasses import dataclass
-
-import dateutil
-import numpy as np
-
-from src.display.formatting import make_clickable_model
-from src.display.utils import AutoEvalColumn, ModelType, Tasks, Precision, WeightType
-from src.submission.check_validity import is_model_on_hub
-
-
-@dataclass
-class EvalResult:
-    """Represents one full evaluation. Built from a combination of the result and request file for a given run.
-    """
-    eval_name: str # org_model_precision (uid)
-    full_model: str # org/model (path on hub)
-    org: str 
-    model: str
-    revision: str # commit hash, "" if main
-    results: dict
-    precision: Precision = Precision.Unknown
-    model_type: ModelType = ModelType.Unknown # Pretrained, fine tuned, ...
-    weight_type: WeightType = WeightType.Original # Original or Adapter
-    architecture: str = "Unknown" 
-    license: str = "?"
-    likes: int = 0
-    num_params: int = 0
-    date: str = "" # submission date of request file
-    still_on_hub: bool = False
-
-    @classmethod
-    def init_from_json_file(self, json_filepath):
-        """Inits the result from the specific model result file"""
-        with open(json_filepath) as fp:
-            data = json.load(fp)
-
-        config = data.get("config")
-
-        # Precision
-        precision = Precision.from_str(config.get("model_dtype"))
-
-        # Get model and org
-        org_and_model = config.get("model_name", config.get("model_args", None))
-        org_and_model = org_and_model.split("/", 1)
-
-        if len(org_and_model) == 1:
-            org = None
-            model = org_and_model[0]
-            result_key = f"{model}_{precision.value.name}"
-        else:
-            org = org_and_model[0]
-            model = org_and_model[1]
-            result_key = f"{org}_{model}_{precision.value.name}"
-        full_model = "/".join(org_and_model)
-
-        still_on_hub, _, model_config = is_model_on_hub(
-            full_model, config.get("model_sha", "main"), trust_remote_code=True, test_tokenizer=False
-        )
-        architecture = "?"
-        if model_config is not None:
-            architectures = getattr(model_config, "architectures", None)
-            if architectures:
-                architecture = ";".join(architectures)
-
-        # Extract results available in this file (some results are split in several files)
-        results = {}
-        for task in Tasks:
-            task = task.value
-
-            # We average all scores of a given metric (not all metrics are present in all files)
-            accs = np.array([v.get(task.metric, None) for k, v in data["results"].items() if task.benchmark == k])
-            if accs.size == 0 or any([acc is None for acc in accs]):
-                continue
-
-            mean_acc = np.mean(accs) * 100.0
-            results[task.benchmark] = mean_acc
-
-        return self(
-            eval_name=result_key,
-            full_model=full_model,
-            org=org,
-            model=model,
-            results=results,
-            precision=precision,  
-            revision= config.get("model_sha", ""),
-            still_on_hub=still_on_hub,
-            architecture=architecture
-        )
-
-    def update_with_request_file(self, requests_path):
-        """Finds the relevant request file for the current model and updates info with it"""
-        request_file = get_request_file_for_model(requests_path, self.full_model, self.precision.value.name)
-
-        try:
-            with open(request_file, "r") as f:
-                request = json.load(f)
-            self.model_type = ModelType.from_str(request.get("model_type", ""))
-            self.weight_type = WeightType[request.get("weight_type", "Original")]
-            self.license = request.get("license", "?")
-            self.likes = request.get("likes", 0)
-            self.num_params = request.get("params", 0)
-            self.date = request.get("submitted_time", "")
-        except Exception:
-            print(f"Could not find request file for {self.org}/{self.model} with precision {self.precision.value.name}")
-
-    def to_dict(self):
-        """Converts the Eval Result to a dict compatible with our dataframe display"""
-        average = sum([v for v in self.results.values() if v is not None]) / len(Tasks)
-        data_dict = {
-            "eval_name": self.eval_name,  # not a column, just a save name,
-            AutoEvalColumn.precision.name: self.precision.value.name,
-            AutoEvalColumn.model_type.name: self.model_type.value.name,
-            AutoEvalColumn.model_type_symbol.name: self.model_type.value.symbol,
-            AutoEvalColumn.weight_type.name: self.weight_type.value.name,
-            AutoEvalColumn.architecture.name: self.architecture,
-            AutoEvalColumn.model.name: make_clickable_model(self.full_model),
-            AutoEvalColumn.revision.name: self.revision,
-            AutoEvalColumn.average.name: average,
-            AutoEvalColumn.license.name: self.license,
-            AutoEvalColumn.likes.name: self.likes,
-            AutoEvalColumn.params.name: self.num_params,
-            AutoEvalColumn.still_on_hub.name: self.still_on_hub,
-        }
-
-        for task in Tasks:
-            data_dict[task.value.col_name] = self.results[task.value.benchmark]
-
-        return data_dict
-
-
-def get_request_file_for_model(requests_path, model_name, precision):
-    """Selects the correct request file for a given model. Only keeps runs tagged as FINISHED"""
-    request_files = os.path.join(
-        requests_path,
-        f"{model_name}_eval_request_*.json",
-    )
-    request_files = glob.glob(request_files)
-
-    # Select correct request file (precision)
-    request_file = ""
-    request_files = sorted(request_files, reverse=True)
-    for tmp_request_file in request_files:
-        with open(tmp_request_file, "r") as f:
-            req_content = json.load(f)
-            if (
-                req_content["status"] in ["FINISHED"]
-                and req_content["precision"] == precision.split(".")[-1]
-            ):
-                request_file = tmp_request_file
-    return request_file
-
-
-def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResult]:
-    """From the path of the results folder root, extract all needed info for results"""
-    model_result_filepaths = []
-
-    for root, _, files in os.walk(results_path):
-        # We should only have json files in model results
-        if len(files) == 0 or any([not f.endswith(".json") for f in files]):
-            continue
-
-        # Sort the files by date
-        try:
-            files.sort(key=lambda x: x.removesuffix(".json").removeprefix("results_")[:-7])
-        except dateutil.parser._parser.ParserError:
-            files = [files[-1]]
-
-        for file in files:
-            model_result_filepaths.append(os.path.join(root, file))
-
-    eval_results = {}
-    for model_result_filepath in model_result_filepaths:
-        # Creation of result
-        eval_result = EvalResult.init_from_json_file(model_result_filepath)
-        eval_result.update_with_request_file(requests_path)
-
-        # Store results of same eval together
-        eval_name = eval_result.eval_name
-        if eval_name in eval_results.keys():
-            eval_results[eval_name].results.update({k: v for k, v in eval_result.results.items() if v is not None})
-        else:
-            eval_results[eval_name] = eval_result
-
-    results = []
-    for v in eval_results.values():
-        try:
-            v.to_dict() # we test if the dict version is complete
-            results.append(v)
-        except KeyError:  # not all eval values present
-            continue
-
-    return results

src/populate.py

@@ -1,58 +0,0 @@
-import json
-import os
-
-import pandas as pd
-
-from src.display.formatting import has_no_nan_values, make_clickable_model
-from src.display.utils import AutoEvalColumn, EvalQueueColumn
-from src.leaderboard.read_evals import get_raw_eval_results
-
-
-def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list) -> pd.DataFrame:
-    """Creates a dataframe from all the individual experiment results"""
-    raw_data = get_raw_eval_results(results_path, requests_path)
-    all_data_json = [v.to_dict() for v in raw_data]
-
-    df = pd.DataFrame.from_records(all_data_json)
-    df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
-    df = df[cols].round(decimals=2)
-
-    # filter out if any of the benchmarks have not been produced
-    df = df[has_no_nan_values(df, benchmark_cols)]
-    return df
-
-
-def get_evaluation_queue_df(save_path: str, cols: list) -> list[pd.DataFrame]:
-    """Creates the different dataframes for the evaluation queues requestes"""
-    entries = [entry for entry in os.listdir(save_path) if not entry.startswith(".")]
-    all_evals = []
-
-    for entry in entries:
-        if ".json" in entry:
-            file_path = os.path.join(save_path, entry)
-            with open(file_path) as fp:
-                data = json.load(fp)
-
-            data[EvalQueueColumn.model.name] = make_clickable_model(data["model"])
-            data[EvalQueueColumn.revision.name] = data.get("revision", "main")
-
-            all_evals.append(data)
-        elif ".md" not in entry:
-            # this is a folder
-            sub_entries = [e for e in os.listdir(f"{save_path}/{entry}") if os.path.isfile(e) and not e.startswith(".")]
-            for sub_entry in sub_entries:
-                file_path = os.path.join(save_path, entry, sub_entry)
-                with open(file_path) as fp:
-                    data = json.load(fp)
-
-                data[EvalQueueColumn.model.name] = make_clickable_model(data["model"])
-                data[EvalQueueColumn.revision.name] = data.get("revision", "main")
-                all_evals.append(data)
-
-    pending_list = [e for e in all_evals if e["status"] in ["PENDING", "RERUN"]]
-    running_list = [e for e in all_evals if e["status"] == "RUNNING"]
-    finished_list = [e for e in all_evals if e["status"].startswith("FINISHED") or e["status"] == "PENDING_NEW_EVAL"]
-    df_pending = pd.DataFrame.from_records(pending_list, columns=cols)
-    df_running = pd.DataFrame.from_records(running_list, columns=cols)
-    df_finished = pd.DataFrame.from_records(finished_list, columns=cols)
-    return df_finished[cols], df_running[cols], df_pending[cols]

src/submission/check_validity.py

@@ -1,99 +0,0 @@
-import json
-import os
-import re
-from collections import defaultdict
-from datetime import datetime, timedelta, timezone
-
-import huggingface_hub
-from huggingface_hub import ModelCard
-from huggingface_hub.hf_api import ModelInfo
-from transformers import AutoConfig
-from transformers.models.auto.tokenization_auto import AutoTokenizer
-
-def check_model_card(repo_id: str) -> tuple[bool, str]:
-    """Checks if the model card and license exist and have been filled"""
-    try:
-        card = ModelCard.load(repo_id)
-    except huggingface_hub.utils.EntryNotFoundError:
-        return False, "Please add a model card to your model to explain how you trained/fine-tuned it."
-
-    # Enforce license metadata
-    if card.data.license is None:
-        if not ("license_name" in card.data and "license_link" in card.data):
-            return False, (
-                "License not found. Please add a license to your model card using the `license` metadata or a"
-                " `license_name`/`license_link` pair."
-            )
-
-    # Enforce card content
-    if len(card.text) < 200:
-        return False, "Please add a description to your model card, it is too short."
-
-    return True, ""
-
-def is_model_on_hub(model_name: str, revision: str, token: str = None, trust_remote_code=False, test_tokenizer=False) -> tuple[bool, str]:
-    """Checks if the model model_name is on the hub, and whether it (and its tokenizer) can be loaded with AutoClasses."""
-    try:
-        config = AutoConfig.from_pretrained(model_name, revision=revision, trust_remote_code=trust_remote_code, token=token)
-        if test_tokenizer:
-            try:
-                tk = AutoTokenizer.from_pretrained(model_name, revision=revision, trust_remote_code=trust_remote_code, token=token)
-            except ValueError as e:
-                return (
-                    False,
-                    f"uses a tokenizer which is not in a transformers release: {e}",
-                    None
-                )
-            except Exception as e:
-                return (False, "'s tokenizer cannot be loaded. Is your tokenizer class in a stable transformers release, and correctly configured?", None)
-        return True, None, config
-
-    except ValueError:
-        return (
-            False,
-            "needs to be launched with `trust_remote_code=True`. For safety reason, we do not allow these models to be automatically submitted to the leaderboard.",
-            None
-        )
-
-    except Exception as e:
-        return False, "was not found on hub!", None
-
-
-def get_model_size(model_info: ModelInfo, precision: str):
-    """Gets the model size from the configuration, or the model name if the configuration does not contain the information."""
-    try:
-        model_size = round(model_info.safetensors["total"] / 1e9, 3)
-    except (AttributeError, TypeError):
-        return 0  # Unknown model sizes are indicated as 0, see NUMERIC_INTERVALS in app.py
-
-    size_factor = 8 if (precision == "GPTQ" or "gptq" in model_info.modelId.lower()) else 1
-    model_size = size_factor * model_size
-    return model_size
-
-def get_model_arch(model_info: ModelInfo):
-    """Gets the model architecture from the configuration"""
-    return model_info.config.get("architectures", "Unknown")
-
-def already_submitted_models(requested_models_dir: str) -> set[str]:
-    """Gather a list of already submitted models to avoid duplicates"""
-    depth = 1
-    file_names = []
-    users_to_submission_dates = defaultdict(list)
-
-    for root, _, files in os.walk(requested_models_dir):
-        current_depth = root.count(os.sep) - requested_models_dir.count(os.sep)
-        if current_depth == depth:
-            for file in files:
-                if not file.endswith(".json"):
-                    continue
-                with open(os.path.join(root, file), "r") as f:
-                    info = json.load(f)
-                    file_names.append(f"{info['model']}_{info['revision']}_{info['precision']}")
-
-                    # Select organisation
-                    if info["model"].count("/") == 0 or "submitted_time" not in info:
-                        continue
-                    organisation, _ = info["model"].split("/")
-                    users_to_submission_dates[organisation].append(info["submitted_time"])
-
-    return set(file_names), users_to_submission_dates

src/submission/submit.py

@@ -1,119 +0,0 @@
-import json
-import os
-from datetime import datetime, timezone
-
-from src.display.formatting import styled_error, styled_message, styled_warning
-from src.envs import API, EVAL_REQUESTS_PATH, TOKEN, QUEUE_REPO
-from src.submission.check_validity import (
-    already_submitted_models,
-    check_model_card,
-    get_model_size,
-    is_model_on_hub,
-)
-
-REQUESTED_MODELS = None
-USERS_TO_SUBMISSION_DATES = None
-
-def add_new_eval(
-    model: str,
-    base_model: str,
-    revision: str,
-    precision: str,
-    weight_type: str,
-    model_type: str,
-):
-    global REQUESTED_MODELS
-    global USERS_TO_SUBMISSION_DATES
-    if not REQUESTED_MODELS:
-        REQUESTED_MODELS, USERS_TO_SUBMISSION_DATES = already_submitted_models(EVAL_REQUESTS_PATH)
-
-    user_name = ""
-    model_path = model
-    if "/" in model:
-        user_name = model.split("/")[0]
-        model_path = model.split("/")[1]
-
-    precision = precision.split(" ")[0]
-    current_time = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
-
-    if model_type is None or model_type == "":
-        return styled_error("Please select a model type.")
-
-    # Does the model actually exist?
-    if revision == "":
-        revision = "main"
-
-    # Is the model on the hub?
-    if weight_type in ["Delta", "Adapter"]:
-        base_model_on_hub, error, _ = is_model_on_hub(model_name=base_model, revision=revision, token=TOKEN, test_tokenizer=True)
-        if not base_model_on_hub:
-            return styled_error(f'Base model "{base_model}" {error}')
-
-    if not weight_type == "Adapter":
-        model_on_hub, error, _ = is_model_on_hub(model_name=model, revision=revision, token=TOKEN, test_tokenizer=True)
-        if not model_on_hub:
-            return styled_error(f'Model "{model}" {error}')
-
-    # Is the model info correctly filled?
-    try:
-        model_info = API.model_info(repo_id=model, revision=revision)
-    except Exception:
-        return styled_error("Could not get your model information. Please fill it up properly.")
-
-    model_size = get_model_size(model_info=model_info, precision=precision)
-
-    # Were the model card and license filled?
-    try:
-        license = model_info.cardData["license"]
-    except Exception:
-        return styled_error("Please select a license for your model")
-
-    modelcard_OK, error_msg = check_model_card(model)
-    if not modelcard_OK:
-        return styled_error(error_msg)
-
-    # Seems good, creating the eval
-    print("Adding new eval")
-
-    eval_entry = {
-        "model": model,
-        "base_model": base_model,
-        "revision": revision,
-        "precision": precision,
-        "weight_type": weight_type,
-        "status": "PENDING",
-        "submitted_time": current_time,
-        "model_type": model_type,
-        "likes": model_info.likes,
-        "params": model_size,
-        "license": license,
-        "private": False,
-    }
-
-    # Check for duplicate submission
-    if f"{model}_{revision}_{precision}" in REQUESTED_MODELS:
-        return styled_warning("This model has been already submitted.")
-
-    print("Creating eval file")
-    OUT_DIR = f"{EVAL_REQUESTS_PATH}/{user_name}"
-    os.makedirs(OUT_DIR, exist_ok=True)
-    out_path = f"{OUT_DIR}/{model_path}_eval_request_False_{precision}_{weight_type}.json"
-
-    with open(out_path, "w") as f:
-        f.write(json.dumps(eval_entry))
-
-    print("Uploading eval file")
-    API.upload_file(
-        path_or_fileobj=out_path,
-        path_in_repo=out_path.split("eval-queue/")[1],
-        repo_id=QUEUE_REPO,
-        repo_type="dataset",
-        commit_message=f"Add {model} to eval queue",
-    )
-
-    # Remove the local file
-    os.remove(out_path)
-
-    return styled_message(
-        "Your request has been submitted to the evaluation queue!\nPlease wait for up to an hour for the model to show in the PENDING list."
-    )

texts.py

@@ -0,0 +1,10 @@
+
+TITLE = """<h1 align="center" id="space-title">KUMO Benchmark</h1>"""
+
+DESCRIPTION = f"""
+## Generative Evaluation of Complex Reasoning in Large Language Models
+
+✨ KUMO is a novel benchmark designed to systematically evaluate the complex reasoning capabilities of Large Language Models (LLMs) through procedurally generated reasoning games. Explore the limits of LLM reasoning and track model performance on our interactive leaderboard.
+
+
+"""