o3-mini
o3-mini is a closed AI model from OpenAI with an index score of 131 (GPT-4 = 100), rank 124 of 217.
131115–147Index score#124 of 217 models
–Price per million tokensno public API price found
–Context windowtokens it reads at once
31 Jan 2025ReleasedReplaced by o4-mini
Where it sitson the frontier
o1 reached this score 2 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workevidence
Novel problemsevidence
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#124of 217 · 131
LMArena · Mathsmaths questions in chat#128of 346 · 1405LMArena · Codingcoding questions in chat#148of 357 · 1434LMArena · Instruction followingfollowing detailed instructions#156of 362 · 1366LMArena · Textoverall chat quality, judged by people#166of 362 · 1364LMArena · Long promptslong, complex requests#161of 340 · 1373LMArena · Creative writingcreative writing#180of 360 · 1312Epoch Capabilities Indexoverall capability from many benchmarks#117of 231 · 140.7Best attop three among current models
Replaced by o4-mini; it no longer leads any category among current models.
Where to use itprices checked 18 Nov 2026
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released31 Jan 2025
Announcementopenai.com ↗
Release entryo3-mini
Scored aso3-mini
Output speed–
Hugging Faceclosed weights