CookingBench

Leaderboard / categories

Quantities & Scaling

Scaling recipes up and down, yields, pan-size math and baker’s percentages.

Ranking

  1. 1GPT-5.4 Mini
    100.0
  2. 2Grok 4.3
    100.0
  3. 3GPT-5.5
    100.0
  4. 4Claude Fable 5
    100.0
  5. 5Claude Opus 4.8
    100.0
  6. 6Gemini 3.5 Flash
    100.0
  7. 7Gemini 3.1 Pro Preview
    100.0
  8. 8Kimi K2.6
    100.0
  9. 9Qwen 3.5 Plus
    100.0
  10. 10Claude Sonnet 4.6
    100.0
  11. 11DeepSeek V4 Pro
    100.0
  12. 12Mistral Large 3
    100.0
  13. 13Llama 4 Maverick
    95.6

Question heatmap (public questions only)

Model001002003004005006007008009010011012013014015016017018019020021022023024025
GPT-5.4 Mini
Grok 4.3
GPT-5.5
Claude Fable 5
Claude Opus 4.8
Gemini 3.5 Flash
Gemini 3.1 Pro Preview
Kimi K2.6
Qwen 3.5 Plus
Claude Sonnet 4.6
DeepSeek V4 Pro
Mistral Large 3
Llama 4 Maverick

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