Llama 3
Meta
rich detail 21 method fields published
Evaluation
Human evaluations of general capabilities (7,000-prompt taxonomy)
Pairwise human evaluation comparing Llama 3 405B with GPT-4 (0125 API), GPT-4o and Claude 3.5 Sonnet on ~7,000 prompts spanning six individual capabilities (English, reasoning, coding, Hindi, Spanish, Portuguese) and three multiturn capabilities; 7-point rating scale with win rates per capability
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.