benchgap
OpenAI · model

o1 benchmark scores

As of 2026-11-21, o1 (OpenAI) has measured scores on 17 benchmarks and estimated scores on 76 more.

BenchmarkScoreSource
AA-GPQA Diamond74.7%measured
AA-HLE7.0%measured
AA-SciCode40.2%estimated ± 3.4 pp, high confidence
AIME2689.9%estimated ± 1.4 pp, medium confidence
Artificial Analysis Intelligence Index15.2%measured
CritPt0.3%measured
GDPval-AA3.7%estimated ± 11.0 pp, low confidence
GPQA Diamond75.7%estimated ± 0.1 pp, medium confidence
HLE12.8%estimated ± 6.5 pp, medium confidence
IFBench68.3%estimated ± 6.6 pp, medium confidence
AA-LCR65.0%measured
LiveCodeBench v682.2%estimated ± 4.7 pp, high confidence
AA-Omniscience Accuracy34.5%measured
SciCode40.7%estimated ± 4.6 pp, high confidence
BrowseComp58.3%estimated ± 13.0 pp, low confidence
IFEval92.2%measured
LongBench v256.1%estimated ± 5.5 pp, medium confidence
τ²-bench results62.6%measured
AA Coding Index39.7%measured
APEX-Agents-AA1.6%estimated ± 11.4 pp, low confidence
BioMysteryBench (human-difficult)6.5%estimated ± 6.8 pp, low confidence
SWE-bench Verified66.2%estimated ± 6.5 pp, medium confidence
BFCL v451.5%estimated ± 8.5 pp, low confidence
SWE-bench Pro57.2%estimated ± 4.7 pp, medium confidence
AA Agentic Index13.3%estimated ± 12.7 pp, low confidence
MMLU-Pro85.8%estimated ± 4.0 pp, medium confidence
AA-IFBench70.3%measured
BBH97.7%estimated ± 2.4 pp, low confidence
FailureSensorIQ64.0%estimated ± 2.1 pp, high confidence
GPQA75.7%measured
MMLU91.8%measured
Vals GPQA Diamond73.2%measured
Vals LiveCodeBench50.3%measured
Vals MMLU-Pro83.5%measured
MMMLU85.4%estimated ± 0.7 pp, medium confidence
Chess Puzzles10.0%measured
AA MMLU-Pro86.5%estimated ± 0.7 pp, medium confidence
ARC-AGI-151.8%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-bench3.6%estimated ± 12.7 pp, low confidence
FrontierCode 1.1 Main13.8%estimated ± 4.6 pp, medium confidence
FrontierMath v2 (Tier 4)0.0%estimated ± 4.0 pp, medium confidence
FrontierMath v2 (Tiers 1-3)14.7%measured
FrontierSWE v20.9%estimated ± 14.3 pp, low confidence
Furniture Assembly25.0%estimated ± 14.1 pp, low confidence
MaxxBench34.1%estimated ± 10.3 pp, low confidence
Mystery Game Puzzles6.3%estimated ± 10.3 pp, low confidence
NYT Connections42.0%estimated ± 12.6 pp, low confidence
Vals SWE-bench62.6%estimated ± 5.5 pp, medium confidence
VulcanBench v376.4%estimated ± 5.6 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)50.4%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)50.2%estimated ± 1.1 pp, low confidence
FrontierPhysics0.0%estimated ± 6.1 pp, low confidence
HLE w/o tools27.3%estimated ± 4.9 pp, high confidence
SpireClimb0.0%estimated ± 10.3 pp, low confidence
StealthMark31.4%estimated ± 9.7 pp, low confidence
ARC-AGI-30.0%estimated ± 8.6 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
SkillsBench official leaderboard (BenchFlow)38.6%estimated ± 6.2 pp, medium confidence
Vibe Code Bench14.5%estimated ± 10.0 pp, low confidence
FACTS Multimodal32.5%estimated ± 5.6 pp, low confidence
ExploitBench9.6%estimated ± 13.4 pp, low confidence
C-Eval90.1%estimated ± 1.0 pp, medium confidence
HMMT Feb 202680.9%estimated ± 3.1 pp, medium confidence
HMMT Nov 202586.2%estimated ± 1.5 pp, low confidence
MMAnswerBench77.5%estimated ± 2.4 pp, low confidence
MMLU-Redux95.3%estimated ± 0.8 pp, medium confidence
NL2Repo27.4%estimated ± 4.7 pp, medium confidence
SuperGPQA55.7%estimated ± 8.5 pp, low confidence
AA LiveCodeBench87.7%estimated ± 4.7 pp, low confidence
HealthBench Hard3.5%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)78.3%estimated ± 4.0 pp, low confidence
React Native Evals74.1%estimated ± 3.2 pp, high confidence
SWE-Rebench0.1%estimated ± 8.9 pp, low confidence
DAYJOB0.4%estimated ± 6.3 pp, low confidence
DAYJOB Healthcare0.1%estimated ± 6.1 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (length-adjusted)54.1%estimated ± 3.7 pp, medium confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HLE-Verified29.0%estimated ± 7.1 pp, low confidence
LABBench279.5%estimated ± 1.8 pp, low confidence
ScarfBench24.4%estimated ± 9.1 pp, low confidence
BlenderWorld (text-only)70.6%estimated ± 4.0 pp, low confidence
Cookie-Bench74.0%estimated ± 2.5 pp, low confidence
STEMBench2.5%estimated ± 0.2 pp, medium confidence
SimpleQA38.0%estimated ± 4.3 pp, low confidence
OpenHarmony Bench v1.042.8%estimated ± 2.8 pp, medium confidence
SEC-Bench Pro16.5%estimated ± 12.3 pp, low confidence
MRCRv245.4%estimated ± 11.3 pp, low confidence
MMLongBench-Doc60.6%estimated ± 2.6 pp, low confidence
BioBasicsBench34.1%estimated ± 3.8 pp, low confidence
ExploitBench Internal Port0.0%estimated ± 1.4 pp, low confidence