Llama 2-13B
Llama 2-13B is an open-weights AI model from Meta with an index score of 87 (GPT-4 = 100), rank 215 of 217.
8771–104Index score#215 of 217 models
–Price per million tokensno public API price found
–Context windowtokens it reads at once
18 Jul 2023Released3 years 4 months ago
Where it sitson the frontier
GPT-4 reached this score 4 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 8 leaderboards
The Model Indexthird-party tests, our method#215of 217 · 87
Epoch Capabilities Indexoverall capability from many benchmarks#197of 231 · 96.3LMArena · Textoverall chat quality, judged by people#329of 362 · 1142LMArena · Instruction followingfollowing detailed instructions#331of 362 · 1110LMArena · Mathsmaths questions in chat#318of 346 · 1111LMArena · Codingcoding questions in chat#329of 357 · 1163LMArena · Creative writingcreative writing#334of 360 · 1091LMArena · Long promptslong, complex requests#317of 340 · 1141Best attop three among current models
Not in the top three among current models on any category we track.
Facts and sources
Released18 Jul 2023
Announcementnot linked yet
Release entry–
Scored asLlama 2-13B
Output speed–
Hugging Facenot linked