Llama 3.1-8B
Llama 3.1-8B is an open-weights AI model from Meta with an index score of 89 (GPT-4 = 100), rank 214 of 217.
8970–107Index score#214 of 217 models
$0.020/ $0.040Price per million tokensinput / output · via OpenRouter
131KContext windowtokens it reads at once
23 Jul 2024Released2 years 4 months ago
Where it sitson the frontier
GPT-4 reached this score 16 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
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#214of 217 · 89
Epoch Capabilities Indexoverall capability from many benchmarks#178of 231 · 110.8LMArena · Codingcoding questions in chat#284of 357 · 1260LMArena · Textoverall chat quality, judged by people#291of 362 · 1211LMArena · Instruction followingfollowing detailed instructions#291of 362 · 1191LMArena · Creative writingcreative writing#290of 360 · 1177LMArena · Mathsmaths questions in chat#286of 346 · 1188LMArena · Long promptslong, complex requests#282of 340 · 1224Best attop three among current models
Not in the top three among current models on any category we track.
Where to use itprices checked 18 Nov 2026
API providers 4 · per 1M tokens, in / out
Run it yourself
Official weightsmeta-llama/Meta-Llama-3.1-8B-Instruct↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released23 Jul 2024
Announcementnot linked yet
Release entry–
Scored asLlama 3.1-8B
Output speed–
Hugging Facemeta-llama/Meta-Llama-3.1-8B-Instruct ↗