Llama 3.2
Llama 3.2 is an open-weights AI model from Meta with an index score of 106 (GPT-4 = 100), rank 188 of 217.
10690–122Index score#188 of 217 models
–Price per million tokensno public API price found
–Context windowtokens it reads at once
25 Sep 2024Released2 years 2 months ago
Where it sitson the frontier
GPT-4 Turbo reached this score 11 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingno evidence yet
Agentsevidence
Professional workno evidence yet
Novel problemsno evidence yet
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 2 leaderboards
The Model Indexthird-party tests, our method#188of 217 · 106
Epoch Capabilities Indexoverall capability from many benchmarks#157of 231 · 122.9Best attop three among current models
Not in the top three among current models on any category we track.
Facts and sources
Released25 Sep 2024
Announcementai.meta.com ↗
Release entryLlama 3.2 (1B/3B text + 11B/90B vision)
Scored asLlama 3.2 90B
Output speed–
Hugging Facenot linked