LLaMA-13B
LLaMA-13B is an open-weights AI model from Meta, released 24 Feb 2023, with no index score yet.
–Index scoreNo third-party results yet
–Price per million tokensno public API price found
–Context windowtokens it reads at once
24 Feb 2023ReleasedReplaced by Llama 2-13B
Where it sitson the frontier
Not plotted: no third-party score yet.
Test resultsby area · tick = best by any model
Reasoning & knowledgeno evidence yet
Mathsevidence
Codingno evidence yet
Agentsno evidence yet
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 6 leaderboards
Epoch Capabilities Indexoverall capability from many benchmarks#208of 231 · 85.0LMArena · Mathsmaths questions in chat#344of 346 · 924LMArena · Creative writingcreative writing#359of 360 · 936LMArena · Textoverall chat quality, judged by people#361of 362 · 975LMArena · Instruction followingfollowing detailed instructions#361of 362 · 919LMArena · Codingcoding questions in chat#357of 357 · 883
Best attop three among current models
Replaced by Llama 2-13B; it no longer leads any category among current models.
Facts and sources
Released24 Feb 2023
Announcementnot linked yet
Release entry–
Scored asLLaMA-13B
Output speed–
Hugging Facenot linked