CookingBench

Which AI model is the best chef?

CookingBench scores models on the things that actually go wrong in a kitchen: scaling quantities, converting units, food safety, substitutions, technique, flavour logic and nutrition math.

Leaderboard · run 2026-06-v1

2026-06-11
#ModelOverallHard setRun cost
1GPT-5.5OpenAI99.398.7$1.42
2Claude Opus 4.8Anthropic99.2100.0$1.16
3Qwen 3.5 PlusAlibaba98.798.6$0.32
4Grok 4.3xAI98.697.0$0.18
5Claude Fable 5Anthropic98.296.0$2.92
6Gemini 3.1 Pro PreviewGoogle97.393.7$1.25
7DeepSeek V4 ProDeepSeek96.693.1$0.19
8Mistral Large 3Mistral95.697.0$0.04
9Llama 4 MaverickMeta90.894.1$0.02
10Kimi K2.6Moonshot AI84.577.8$0.52

Categories