benchgap
OpenAI · model

GPT-5.1-Codex-Max benchmark scores

As of 2026-11-22, GPT-5.1-Codex-Max (OpenAI) has measured scores on 13 benchmarks and estimated scores on 84 more.

BenchmarkScoreSource
AA-GPQA Diamond86.0%measured
AA-HLE25.7%measured
AA-SciCode48.9%estimated ± 3.8 pp, high confidence
Artificial Analysis Intelligence Index23.7%measured
CritPt5.7%measured
GDPval-AA15.9%estimated ± 11.0 pp, low confidence
GPQA Diamond85.1%estimated ± 2.4 pp, high confidence
HLE27.8%estimated ± 8.5 pp, medium confidence
IFBench68.0%estimated ± 6.6 pp, medium confidence
AA-LCR69.3%measured
LiveCodeBench v688.1%estimated ± 2.2 pp, medium confidence
AA-Omniscience Accuracy39.9%measured
SciCode43.9%estimated ± 2.9 pp, low confidence
BrowseComp68.1%estimated ± 13.0 pp, low confidence
HLE w/ tools36.0%estimated ± 5.5 pp, low confidence
IFEval92.8%estimated ± 2.8 pp, high confidence
LongBench v258.1%estimated ± 5.5 pp, medium confidence
τ²-bench results83.0%measured
AA Coding Index51.0%estimated ± 6.9 pp, medium confidence
AA-MMMU-Pro72.5%measured
APEX-Agents-AA2.2%estimated ± 11.4 pp, low confidence
BioMysteryBench (human-difficult)38.6%estimated ± 6.8 pp, low confidence
SWE-bench Verified82.1%estimated ± 3.2 pp, medium confidence
BFCL v463.0%estimated ± 8.5 pp, low confidence
SWE-bench Pro54.7%estimated ± 2.9 pp, medium confidence
AA Agentic Index20.5%estimated ± 12.7 pp, low confidence
MMLU-Pro85.5%estimated ± 5.0 pp, medium confidence
AA-IFBench70.0%measured
FailureSensorIQ64.6%estimated ± 2.8 pp, low confidence
GPQA86.8%estimated ± 6.1 pp, medium confidence
MMLU90.5%estimated ± 0.9 pp, medium confidence
Vals GPQA Diamond85.1%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench83.6%measured
Vals MMLU-Pro87.3%estimated ± 2.9 pp, high confidence
MMMLU88.6%estimated ± 0.7 pp, medium confidence
MMMU81.8%estimated ± 2.7 pp, high confidence
AA MMLU-Pro87.2%estimated ± 0.8 pp, high confidence
ARC-AGI-179.0%estimated ± 7.8 pp, low confidence
ARC-AGI-241.5%estimated ± 14.4 pp, low confidence
CursorBench 3.259.1%estimated ± 7.2 pp, low confidence
FrontierCode 1.1 Main37.4%estimated ± 6.2 pp, medium confidence
Mystery Game Puzzles14.1%estimated ± 2.2 pp, low confidence
OfficeQA Pro50.3%estimated ± 6.8 pp, low confidence
ParseBench-156.4%estimated ± 6.2 pp, medium confidence
Vals SWE-bench77.1%estimated ± 2.8 pp, high confidence
VulcanBench v382.7%estimated ± 5.6 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)53.0%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)44.5%estimated ± 0.8 pp, low confidence
Chartography (tools)78.6%estimated ± 4.1 pp, low confidence
CursorBench 4.040.4%estimated ± 4.5 pp, high confidence
HLE w/o tools34.8%estimated ± 4.9 pp, high confidence
PostTrainBench v1.118.2%estimated ± 1.3 pp, low confidence
ARC-AGI-31.3%estimated ± 9.8 pp, medium confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
SkillsBench official leaderboard (BenchFlow)37.3%estimated ± 11.3 pp, low confidence
BinaryAudit11.4%estimated ± 8.8 pp, medium confidence
OTelBench11.6%measured
Vibe Code Bench22.2%measured
ParseBench-261.2%estimated ± 6.2 pp, medium confidence
CharXiv79.3%estimated ± 6.3 pp, low confidence
CharXiv w/o tools78.6%estimated ± 2.5 pp, medium confidence
AI2D_TEST88.7%estimated ± 2.0 pp, medium confidence
C-Eval92.7%estimated ± 1.0 pp, medium confidence
CountBench93.3%estimated ± 2.9 pp, medium confidence
DynaMath83.6%estimated ± 3.0 pp, medium confidence
ERQA51.9%estimated ± 3.1 pp, high confidence
MathVision81.8%estimated ± 3.1 pp, high confidence
MMLU-Redux96.0%estimated ± 0.8 pp, medium confidence
MMMU-Pro73.9%estimated ± 1.5 pp, high confidence
NL2Repo45.7%estimated ± 7.9 pp, low confidence
PostTrainBench v119.7%measured
RealWorldQA81.4%estimated ± 2.9 pp, medium confidence
ScreenSpot Pro72.9%estimated ± 10.8 pp, low confidence
SuperGPQA81.1%estimated ± 9.3 pp, medium confidence
V*89.0%estimated ± 7.5 pp, medium confidence
Video-MME (w/o subtitle)81.3%estimated ± 1.7 pp, medium confidence
Video-MME (with subtitle)83.4%estimated ± 3.7 pp, medium confidence
AA LiveCodeBench87.6%estimated ± 3.4 pp, low confidence
HealthBench Hard24.8%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)64.5%estimated ± 6.5 pp, low confidence
React Native Evals70.3%estimated ± 3.0 pp, low confidence
SWE-Rebench41.1%estimated ± 6.5 pp, low confidence
PostTrainBench17.2%estimated ± 1.2 pp, low confidence
BioMysteryBench (human-solvable)81.8%estimated ± 0.6 pp, low confidence
HealthBench (raw)34.3%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)48.1%estimated ± 3.4 pp, low confidence
HealthBench Professional56.8%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)45.8%estimated ± 4.5 pp, medium confidence
HLE-Verified34.6%estimated ± 7.1 pp, low confidence
LABBench273.7%estimated ± 2.4 pp, low confidence
STEMBench2.5%estimated ± 0.2 pp, medium confidence
SimpleQA45.4%estimated ± 4.3 pp, low confidence
BabyVision w/ Python86.0%estimated ± 4.0 pp, low confidence
MRCRv271.1%estimated ± 11.3 pp, low confidence
MMLongBench-Doc60.9%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
MMMU-Pro w/ Python76.0%estimated ± 2.0 pp, high confidence