o3-mini

OpenAIReleased 31 Jan 2025ClosedReasoningDate verified

Compare Announcement

132121–144Index score#109 of 229 models

3/ 8Core tests taken3 of 6 areas · plus 17 anchor tests

−3Versus the frontier at releasebest then: o1Replaced by o4-mini

$1.1/ $4.4Price per million tokensinput / output, list price

200KContext windowtokens it reads at once

Where it sitson the frontier

o1 reached this score 2 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence

GPQA Diamond

77%

Humanity's Last Exam

no result

Mathsevidence

FrontierMath T1-3

19%

Codingevidence

SWE-bench Verified

no result

Terminal-Bench

no result

Agentsevidence

APEX-Agents

no result

Novel problemsevidence

ARC-AGI-2

Long tasksno evidence yet

METR time horizon

no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

What others sayrank on each leaderboard

The Model Indexindependent tests, our method#109of 219 · 132

LMArena · Mathsmaths questions in chat#130of 373 · 1405 LMArena · Codingcoding questions in chat#155of 383 · 1434 Epoch Capabilities Indexoverall capability from many benchmarks#103of 239 · 140.3 LMArena · Textoverall chat quality, judged by people#179of 388 · 1364 LMArena · Creative writingcreative writing#194of 386 · 1312

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.