Llama 3.3 70B
Llama 3.3 70B is an open-weights AI model from Meta with an index score of 108 (GPT-4 = 100), rank 183 of 217.
10892–124Index score#183 of 217 models
$0.71/ $0.71Price per million tokensinput / output · via OpenRouter
131KContext windowtokens it reads at once
6 Dec 2024Released1 year 11 months ago
Where it sitson the frontier
GPT-4 Turbo (Apr 2024) reached this score 8 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#183of 217 · 108
LMArena · Creative writingcreative writing#212of 360 · 1285LMArena · Mathsmaths questions in chat#207of 346 · 1296LMArena · Textoverall chat quality, judged by people#219of 362 · 1318LMArena · Instruction followingfollowing detailed instructions#227of 362 · 1293LMArena · Codingcoding questions in chat#229of 357 · 1346Epoch Capabilities Indexoverall capability from many benchmarks#151of 231 · 126.2LMArena · Long promptslong, complex requests#227of 340 · 1314Best 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 7 · per 1M tokens, in / out
Run it yourself
Official weightsmeta-llama/Llama-3.3-70B-Instruct↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released6 Dec 2024
Announcementabout.fb.com ↗
Release entryLlama 3.3 70B
Scored asLlama 3.3 70B
Output speed–
Hugging Facemeta-llama/Llama-3.3-70B-Instruct ↗