hardcorelogic.summary.json

[
  {
    "model": "Qwen3-8B",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 12.37,
    "increased complexity": 15.08,
    "uncommon elements": 10.58,
    "unsolvable puzzle": 69.54,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "Qwen3-30B-A3B-Thinking-2507",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 37.33,
    "increased complexity": "",
    "uncommon elements": "" ,
    "unsolvable puzzle": 86.09,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "Qwen3-32B",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 20.97,
    "increased complexity": 25.38 ,
    "uncommon elements": 16.93 ,
    "unsolvable puzzle": 65.48,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "Qwen3-Next-80B-A3B-Thinking",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 36.35,
    "increased complexity": 41.97,
    "uncommon elements": 32.13 ,
    "unsolvable puzzle": 83.11,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "Qwen3-235B-A22B-Thinking-2507",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 43.33,
    "increased complexity": 46.93,
    "uncommon elements": 40.94 ,
    "unsolvable puzzle": 84.41,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "MiniMax-M1-40k",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 6.44,
    "increased complexity": 5.27,
    "uncommon elements": 6.88 ,
    "unsolvable puzzle": 51.39,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "DeepSeek-R1-0528-Qwen3-8B",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 13.83,
    "increased complexity": "",
    "uncommon elements": "" ,
    "unsolvable puzzle": 95.19,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "DeepSeek-V3.1",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 41.43,
    "increased complexity": 44.61,
    "uncommon elements": 39.09 ,
    "unsolvable puzzle": 88.76,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "DeepSeek-R1-0528",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 41.37,
    "increased complexity": 45.87,
    "uncommon elements": 37.28 ,
    "unsolvable puzzle": 93.50,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "GLM-4.5",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 21.67,
    "increased complexity": 24.17,
    "uncommon elements": 21.49,
    "unsolvable puzzle": 93.26,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "Kimi-K2-Instruct",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 15.18,
    "increased complexity": 17.33,
    "uncommon elements": 14.71,
    "unsolvable puzzle": 87.46,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "Seed-OSS-36B-Instruct",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 38.96,
    "increased complexity": 41.01,
    "uncommon elements": 38.79 ,
    "unsolvable puzzle": 85.76,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "gpt-oss-120b",
    "mode": "sampling (Temp=0.6)",
    "open-source": true,
    "total accuracy": 51.97,
    "increased complexity": 54.08,
    "uncommon elements": 51.11,
    "unsolvable puzzle": 93.35,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 50
  },
  {
    "model": "gpt-5",
    "mode": "sampling (Temp=0.6)",
    "open-source": false,
    "total accuracy": 69.10,
    "increased complexity": 69.89,
    "uncommon elements": 67.88,
    "unsolvable puzzle": 97.78,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 5
  },
  {
    "model": "gpt-5-mini",
    "mode": "sampling (Temp=0.6)",
    "open-source": false,
    "total accuracy": 54.49,
    "increased complexity": 55.76,
    "uncommon elements": 52.13 ,
    "unsolvable puzzle": 98.52,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 5
  },
  {
    "model": "o4-mini",
    "mode": "sampling (Temp=0.6)",
    "open-source": false,
    "total accuracy": 50.13,
    "increased complexity": 55.11,
    "uncommon elements": 47.13 ,
    "unsolvable puzzle": 95.00,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 5
  },
  {
    "model": "grok-4",
    "mode": "sampling (Temp=0.6)",
    "open-source": false,
    "total accuracy": 59.55,
    "increased complexity": 58.26 ,
    "uncommon elements": 59.62 ,
    "unsolvable puzzle": 97.59,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 5
  },
  {
    "model": "gemini-2.5-pro",
    "mode": "sampling (Temp=0.6)",
    "open-source": false,
    "total accuracy": 40.58,
    "increased complexity": 43.80,
    "uncommon elements": 39.38 ,
    "unsolvable puzzle": 91.48,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 5
  },
  {
    "model": "grok-3-mini",
    "mode": "sampling (Temp=0.6)",
    "open-source": false,
    "total accuracy": 42.56,
    "increased complexity": 48.48,
    "uncommon elements": 39.5,
    "unsolvable puzzle": 94.63,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 5
  },
  {
    "model": "claude-sonnet-4-thinking",
    "mode": "sampling (Temp=0.6)",
    "open-source": false,
    "total accuracy": 30.51,
    "increased complexity": 34.67,
    "uncommon elements": 28.25 ,
    "unsolvable puzzle": 57.96,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 5
  },
  {
    "model": "gemini-2.5-flash",
    "mode": "sampling (Temp=0.6)",
    "open-source": false,
    "total accuracy": 19.49,
    "increased complexity": 25.11,
    "uncommon elements": 16.00,
    "unsolvable puzzle": 57.78,
    "temperature": 0.6,
    "n_sampling": 4,
    "n": 5
  }
]