CookingBench

Leaderboard / categories

Nutrition

Calorie and macro math, per-serving calculations and label reasoning.

Ranking

  1. 1GPT-5.4 Mini
    100.0
  2. 2Claude Fable 5
    100.0
  3. 3Grok 4.3
    90.0
  4. 4GPT-5.5
    90.0
  5. 5Claude Opus 4.8
    90.0
  6. 6Gemini 3.5 Flash
    90.0
  7. 7Gemini 3.1 Pro Preview
    90.0
  8. 8Kimi K2.6
    90.0
  9. 9Qwen 3.5 Plus
    90.0
  10. 10DeepSeek V4 Pro
    90.0
  11. 11Mistral Large 3
    85.0
  12. 12Claude Sonnet 4.6
    80.0
  13. 13Llama 4 Maverick
    65.0

Question heatmap (public questions only)

Model001002003004005006007008009010011012013014015016020021022023024025026027028029030031032033034035036037038039
GPT-5.4 Mini
Claude Fable 5
Grok 4.3
GPT-5.5
Claude Opus 4.8
Gemini 3.5 Flash
Gemini 3.1 Pro Preview
Kimi K2.6
Qwen 3.5 Plus
DeepSeek V4 Pro
Mistral Large 3
Claude Sonnet 4.6
Llama 4 Maverick

Each cell is one question; deeper colour = higher score. Hover for exact values.