Preference
Sustainable Food Recipe Preference Prediction
Recipe preference prediction: six LLMs pick which of two comparable Food.com recipes is preferred by users; scored against the truly higher-rated recipe. 500 pairs x 6 models, binary correctness.
500items
6subjects
MITlicense
preferencedomain
textmodality
item-level responses released
Saturation status: Unknown
Response matrix
Fit to width. Hover for subject & item; click a cell for details.
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect
Subjects
- 1GPT-4o0.64
- 2Claude 3.5 Sonnet0.6333
- 3o1-preview0.596
- 4GPT-3.5 Turbo0.566
- 5Llama 3.1 70B Instruct0.506
- 6Gemini 1.5 Pro0.478