benchgap
OpenAI · model

o3-mini benchmark scores

As of 2026-11-21, o3-mini (OpenAI) has measured scores on 14 benchmarks and estimated scores on 63 more.

BenchmarkScoreSource
AA-GPQA Diamond74.8%measured
AA-HLE7.9%measured
AA-SciCode32.9%estimated ± 3.8 pp, high confidence
Artificial Analysis Intelligence Index12.5%measured
CritPt0.3%estimated ± 0.3 pp, high confidence
GDPval-AA0.1%estimated ± 11.0 pp, low confidence
GPQA Diamond77.2%estimated ± 0.1 pp, medium confidence
HLE14.1%estimated ± 6.5 pp, medium confidence
IFBench72.6%estimated ± 9.2 pp, medium confidence
LiveCodeBench v682.5%estimated ± 2.2 pp, low confidence
AA-Omniscience Accuracy18.5%estimated ± 2.4 pp, high confidence
SciCode32.3%estimated ± 3.6 pp, high confidence
BrowseComp34.5%estimated ± 13.0 pp, low confidence
IFEval93.9%measured
τ²-bench results28.7%measured
AA Coding Index24.4%estimated ± 5.3 pp, medium confidence
APEX-Agents-AA1.6%estimated ± 11.4 pp, low confidence
BioMysteryBench (human-difficult)13.5%estimated ± 8.1 pp, low confidence
SWE-bench Verified49.3%measured
BFCL v427.4%estimated ± 8.5 pp, low confidence
SWE-bench Pro24.5%estimated ± 4.5 pp, high confidence
AA Agentic Index1.3%estimated ± 12.7 pp, low confidence
MMLU-Pro75.5%estimated ± 4.0 pp, high confidence
AA-IFBench71.4%estimated ± 8.8 pp, medium confidence
AIME 202487.3%measured
BBH92.0%estimated ± 2.4 pp, low confidence
FailureSensorIQ64.4%estimated ± 2.1 pp, high confidence
GPQA77.2%measured
MMLU86.9%measured
Vals GPQA Diamond75.5%measured
Vals LiveCodeBench71.5%measured
Vals MMLU-Pro78.7%measured
MATH-50097.4%estimated ± 1.3 pp, medium confidence
MMMLU85.9%estimated ± 1.7 pp, high confidence
Chess Puzzles15.0%measured
AIME 202581.3%estimated ± 3.5 pp, high confidence
AA MMLU-Pro83.5%estimated ± 1.1 pp, medium confidence
ARC-AGI-157.3%estimated ± 6.5 pp, low confidence
ARC-AGI-20.0%estimated ± 10.9 pp, low confidence
CursorBench 3.259.1%estimated ± 7.2 pp, low confidence
EBR-bench0.0%estimated ± 10.4 pp, low confidence
Furniture Assembly32.9%estimated ± 9.3 pp, medium confidence
MaxxBench47.2%estimated ± 8.8 pp, medium confidence
Mystery Game Puzzles7.0%measured
NYT Connections53.7%estimated ± 12.6 pp, low confidence
Vals SWE-bench34.9%estimated ± 6.6 pp, low confidence
VulcanBench v378.2%estimated ± 5.6 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)49.6%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)46.2%estimated ± 1.1 pp, low confidence
CursorBench 4.029.8%estimated ± 4.5 pp, medium confidence
FrontierPhysics2.5%estimated ± 5.0 pp, low confidence
HLE w/o tools24.6%estimated ± 4.9 pp, high confidence
SpireClimb0.0%estimated ± 9.3 pp, medium confidence
StealthMark32.1%estimated ± 9.2 pp, medium confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
SkillsBench official leaderboard (BenchFlow)44.9%estimated ± 6.2 pp, medium confidence
CompileBench55.6%estimated ± 10.0 pp, low confidence
Vibe Code Bench0.0%estimated ± 8.4 pp, low confidence
FACTS Multimodal34.4%estimated ± 5.6 pp, low confidence
ExploitBench14.6%estimated ± 7.2 pp, low confidence
C-Eval89.3%estimated ± 1.0 pp, medium confidence
MMLU-Redux91.8%estimated ± 1.2 pp, medium confidence
NL2Repo45.7%estimated ± 7.9 pp, low confidence
SuperGPQA57.6%estimated ± 8.5 pp, low confidence
React Native Evals65.8%estimated ± 2.7 pp, low confidence
DAYJOB1.3%estimated ± 3.2 pp, high confidence
DAYJOB Healthcare0.7%estimated ± 4.2 pp, high confidence
HealthBench (length-adjusted)54.1%estimated ± 3.7 pp, medium confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
BlenderWorld (text-only)70.0%estimated ± 2.8 pp, low confidence
Cookie-Bench76.9%estimated ± 1.3 pp, low confidence
SimpleQA26.0%estimated ± 7.8 pp, medium confidence
LiveCodeBench57.6%estimated ± 14.6 pp, low confidence
SEC-Bench Pro33.7%estimated ± 9.3 pp, medium confidence
BioBasicsBench15.4%estimated ± 10.2 pp, low confidence
ExploitBench Internal Port0.0%estimated ± 1.4 pp, low confidence