146135–158Index score#65 of 229 models
2/ 8Core tests taken2 of 6 areas · plus 4 anchor tests
−24Versus the frontier at releasebest then: GPT-5.3-CodexReplaced by MiniMax-M2.7 $0.27/ $1.08Price per million tokensinput / output, list price
205KContext windowtokens it reads at once
Where it sitson the frontier
o3 reached this score 10 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeno evidence yet
Humanity's Last Examno result Mathsevidence
FrontierMath T1-3no result Codingevidence
SWE-bench Verifiedno result Long tasksno evidence yet
METR time horizonno 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.