Prompting and multiple-choice (MCQ) benchmarks to evaluate reasoning capabilities of LLMs using Mastermind.
AI & ML interests
None defined yet.
Recent Activity
View all activity
models
28
flair/ner-french
Token Classification
•
Updated
•
3.14k
•
15
flair/ner-multi
Token Classification
•
Updated
•
5.38k
•
10
flair/upos-multi
Token Classification
•
Updated
•
19.9k
•
7
flair/de-pos-fine-grained
Updated
•
10
flair/bueble-lm-2b
Text Generation
•
2B
•
Updated
•
47
•
22
flair/ner-english
Token Classification
•
Updated
•
272k
•
36
flair/ner-english-fast
Token Classification
•
Updated
•
627k
•
25
flair/frame-english-fast
Token Classification
•
Updated
•
336
•
1
flair/frame-english
Token Classification
•
Updated
•
19
•
1
flair/ner-german-legal
Token Classification
•
Updated
•
1.68k
•
24
datasets
13
flair/mastermind_35_mcq_close
Viewer
•
Updated
•
37.1k
•
704
flair/mastermind_24_prompt
Viewer
•
Updated
•
30.4k
•
11
flair/mastermind_46_mcq_close
Viewer
•
Updated
•
36.1k
•
701
flair/mastermind_46_mcq_random
Viewer
•
Updated
•
36.1k
•
698
flair/mastermind_35_mcq_random
Viewer
•
Updated
•
37.1k
•
703
flair/mastermind_24_mcq_close
Viewer
•
Updated
•
30.4k
•
704
flair/mastermind_24_mcq_random
Viewer
•
Updated
•
30.4k
•
709
flair/mastermind_46_prompt
Viewer
•
Updated
•
36.1k
•
12
flair/mastermind_35_prompt
Viewer
•
Updated
•
37.1k
•
10
flair/nuner_entropy_splits
Viewer
•
Updated
•
618k
•
8