Models
7 models evaluated · click through for per-model detail
Anthropic
Claude 4.6 Sonnet
anthropic/claude-4.6-sonnet-20260217
0.1609 questions
OpenAI
GPT-5.1
openai/gpt-5.1-20251113
0.21322 questions
OpenAI
GPT-5.1
gpt-5.1-2025-11-13
0.26827 questions
Google DeepMind
Gemini 2.5 Pro
google/gemini-2.5-pro
0.34420 questions
Anthropic
Claude 4.5 Sonnet
anthropic/claude-4.5-sonnet-20250929
0.53220 questions
DeepSeek
DeepSeek R1
deepseek/deepseek-r1
0.58820 questions
Meta
Llama 3.3 70B
meta-llama/llama-3.3-70b-instruct
2.96720 questions
Mean Cramér-log across each model's GT-scored questions (lower is better). Coverage varies by model, so this isn't apples-to-apples — see the leaderboard for the matched-question board.