Llama 3.2 1B
Llama 3.2 1B is an open-weights AI model from Meta with an index score of 81 (GPT-4 = 100), rank 217 of 217.
8139–124Index score#217 of 217 models
$0.027/ $0.20Price per million tokensinput / output · via OpenRouter
60KContext windowtokens it reads at once
24 Sep 2024Released2 years 2 months ago
Where it sitson the frontier
GPT-4 reached this score 18 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 7 leaderboards
The Model Indexthird-party tests, our method#217of 217 · 81
LMArena · Mathsmaths questions in chat#311of 346 · 1124LMArena · Codingcoding questions in chat#336of 357 · 1149LMArena · Creative writingcreative writing#341of 360 · 1082LMArena · Instruction followingfollowing detailed instructions#343of 362 · 1086LMArena · Textoverall chat quality, judged by people#344of 362 · 1111LMArena · Long promptslong, complex requests#331of 340 · 1103Best 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 1 · per 1M tokens, in / out
Run it yourself
Official weightsmeta-llama/Llama-3.2-1B-Instruct↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released24 Sep 2024
Announcementnot linked yet
Release entry–
Scored asLlama 3.2 1B
Output speed–
Hugging Facemeta-llama/Llama-3.2-1B-Instruct ↗