benchgap
OpenAI · model

o1-preview benchmark scores

As of 2026-11-21, o1-preview (OpenAI) has measured scores on 3 benchmarks and estimated scores on 39 more.

BenchmarkScoreSource
AA-GPQA Diamond76.5%measured
AA-HLE12.1%estimated ± 2.7 pp, high confidence
AA-SciCode37.6%estimated ± 3.4 pp, high confidence
Artificial Analysis Intelligence Index11.4%measured
CritPt0.5%estimated ± 3.8 pp, high confidence
GPQA Diamond85.8%estimated ± 2.6 pp, high confidence
HLE19.8%estimated ± 10.1 pp, low confidence
LiveCodeBench v680.1%estimated ± 4.7 pp, high confidence
AA-Omniscience Accuracy21.9%estimated ± 7.3 pp, medium confidence
SciCode38.2%estimated ± 4.6 pp, high confidence
AA Coding Index34.1%measured
BioMysteryBench (human-difficult)36.2%estimated ± 8.3 pp, low confidence
SWE-bench Verified60.8%estimated ± 6.5 pp, medium confidence
SWE-bench Pro40.4%estimated ± 6.0 pp, medium confidence
MMLU-Pro80.5%estimated ± 5.4 pp, medium confidence
GPQA78.2%estimated ± 6.1 pp, medium confidence
MMLU89.7%estimated ± 3.8 pp, high confidence
Vals GPQA Diamond75.6%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench68.8%estimated ± 7.1 pp, medium confidence
Vals MMLU-Pro82.4%estimated ± 3.0 pp, high confidence
MMMLU86.4%estimated ± 1.7 pp, high confidence
AA MMLU-Pro84.2%estimated ± 1.2 pp, medium confidence
ARC-AGI-174.2%estimated ± 7.9 pp, low confidence
ARC-AGI-226.4%estimated ± 14.6 pp, low confidence
FrontierSWE v20.4%estimated ± 14.3 pp, low confidence
Vals SWE-bench57.6%estimated ± 5.5 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)49.3%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)44.3%estimated ± 1.1 pp, low confidence
HLE w/o tools25.0%estimated ± 4.9 pp, high confidence
Vibe Code Bench11.3%estimated ± 10.0 pp, low confidence
C-Eval89.0%estimated ± 1.0 pp, medium confidence
MMLU-Redux91.3%estimated ± 1.2 pp, medium confidence
NL2Repo22.8%estimated ± 4.7 pp, medium confidence
SuperGPQA61.7%estimated ± 10.1 pp, low confidence
AA LiveCodeBench84.0%estimated ± 4.7 pp, low confidence
React Native Evals72.6%estimated ± 3.2 pp, high confidence
SWE-Rebench0.0%estimated ± 8.9 pp, low confidence
HealthBench (length-adjusted)54.1%estimated ± 3.7 pp, medium confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
ScarfBench24.4%estimated ± 9.1 pp, low confidence
SimpleQA26.8%estimated ± 7.8 pp, medium confidence
BioBasicsBench14.2%estimated ± 10.2 pp, low confidence