benchgap
OpenAI · model

GPT-4.1 benchmark scores

As of 2026-11-22, GPT-4.1 (OpenAI) has measured scores on 21 benchmarks and estimated scores on 106 more.

BenchmarkScoreSource
AA-GPQA Diamond66.6%measured
AA-HLE4.2%measured
AA-SciCode35.8%estimated ± 3.8 pp, high confidence
AIME2678.4%estimated ± 1.4 pp, medium confidence
Artificial Analysis Intelligence Index12.7%measured
CritPt0.0%measured
GDPval-AA14.7%estimated ± 10.5 pp, low confidence
GPQA Diamond66.6%estimated ± 1.2 pp, high confidence
HLE7.2%estimated ± 6.5 pp, medium confidence
IFBench54.5%estimated ± 6.6 pp, medium confidence
AA-LCR68.3%measured
AA-Omniscience Accuracy27.8%measured
SciCode35.2%estimated ± 3.6 pp, high confidence
BrowseComp63.6%estimated ± 8.8 pp, low confidence
HLE w/ tools39.6%estimated ± 5.7 pp, low confidence
IFEval87.4%measured
LongBench v257.6%estimated ± 5.5 pp, medium confidence
τ²-bench results47.1%measured
AA Coding Index25.6%estimated ± 5.3 pp, medium confidence
AA-MMMU-Pro61.2%measured
APEX-Agents-AA8.5%estimated ± 9.3 pp, low confidence
BioMysteryBench (human-difficult)0.0%estimated ± 6.8 pp, low confidence
SWE-bench Verified54.6%measured
BFCL v441.4%estimated ± 8.5 pp, low confidence
CyberGym38.7%estimated ± 11.0 pp, low confidence
JobBench13.3%estimated ± 14.2 pp, low confidence
SWE-bench Pro30.4%estimated ± 4.5 pp, high confidence
WideResearch60.4%estimated ± 3.3 pp, medium confidence
AA Agentic Index11.3%estimated ± 9.4 pp, low confidence
MMLU-Pro82.3%estimated ± 4.0 pp, high confidence
AA-IFBench43.0%measured
BBH95.9%estimated ± 2.4 pp, low confidence
FailureSensorIQ64.1%estimated ± 2.1 pp, high confidence
GPQA66.3%measured
MMLU90.2%measured
Vals GPQA Diamond65.4%measured
Vals LiveCodeBench54.7%measured
Vals MMLU-Pro80.5%measured
MMMLU83.3%estimated ± 0.7 pp, medium confidence
MMMU73.9%estimated ± 2.7 pp, high confidence
Chess Puzzles11.0%measured
AA MMLU-Pro85.3%estimated ± 0.8 pp, high confidence
Gert Labs18.9%measured
ApprenticeBench3.1%estimated ± 10.4 pp, low confidence
ARC-AGI-133.4%estimated ± 6.5 pp, low confidence
ARC-AGI-20.0%estimated ± 13.8 pp, low confidence
CursorBench 3.259.1%estimated ± 7.2 pp, low confidence
EBR-bench4.1%estimated ± 12.7 pp, low confidence
FrontierMath v2 (Tier 4)0.0%estimated ± 4.0 pp, medium confidence
FrontierMath v2 (Tiers 1-3)6.0%measured
Furniture Assembly25.1%estimated ± 14.1 pp, low confidence
MaxxBench34.7%estimated ± 10.3 pp, low confidence
MazeBench0.0%estimated ± 2.7 pp, medium confidence
Mystery Game Puzzles6.4%estimated ± 4.7 pp, medium confidence
NYT Connections44.6%estimated ± 12.6 pp, low confidence
OSWorld-Verified60.3%estimated ± 8.6 pp, low confidence
ParseBench-146.9%estimated ± 6.2 pp, medium confidence
Vals SWE-bench42.0%estimated ± 6.6 pp, low confidence
VulcanBench v376.5%estimated ± 5.6 pp, low confidence
CWE-Bench-AA29.9%estimated ± 8.1 pp, low confidence
AA Cyber Index2.3%estimated ± 12.4 pp, low confidence
DeepsecBench-AA5.4%estimated ± 8.2 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)49.7%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)46.5%estimated ± 1.1 pp, low confidence
AA ITBench35.6%estimated ± 4.6 pp, low confidence
CWE-bench v132.2%estimated ± 5.7 pp, low confidence
FrontierPhysics0.0%estimated ± 6.1 pp, low confidence
HLE w/o tools24.9%estimated ± 4.9 pp, high confidence
OSWorld 2.10.8%estimated ± 3.6 pp, medium confidence
SpireClimb0.0%estimated ± 10.3 pp, low confidence
StealthMark31.9%estimated ± 9.7 pp, low confidence
Toolathlon-Verified53.3%estimated ± 3.0 pp, high confidence
AA AutomationBench37.2%estimated ± 9.9 pp, low confidence
GDP.pdf9.1%estimated ± 4.2 pp, medium confidence
ARC-AGI-30.0%estimated ± 8.6 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
CWE-bench24.7%estimated ± 6.2 pp, low confidence
MKA32.7%estimated ± 4.6 pp, medium confidence
SkillsBench official leaderboard (BenchFlow)40.1%estimated ± 6.2 pp, medium confidence
CompileBench53.3%measured
Vibe Code Bench0.0%estimated ± 8.4 pp, low confidence
FACTS Multimodal32.9%estimated ± 5.6 pp, low confidence
Hermes Index13.7%estimated ± 5.7 pp, low confidence
ParseBench-247.5%estimated ± 6.2 pp, medium confidence
CharXiv71.3%estimated ± 6.3 pp, low confidence
ExploitBench10.6%estimated ± 13.4 pp, low confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
AI2D_TEST88.0%estimated ± 2.0 pp, medium confidence
C-Eval89.4%estimated ± 1.0 pp, medium confidence
ERQA41.2%estimated ± 3.1 pp, medium confidence
HMMT Feb 202678.4%estimated ± 3.1 pp, medium confidence
HMMT Nov 202573.1%estimated ± 1.5 pp, low confidence
MathVision59.2%estimated ± 3.1 pp, medium confidence
MMAnswerBench75.3%estimated ± 2.4 pp, low confidence
MMLU-ProX72.7%measured
MMLU-Redux94.5%estimated ± 0.8 pp, medium confidence
MMMU-Pro62.4%estimated ± 1.5 pp, high confidence
NL2Repo7.2%estimated ± 6.2 pp, low confidence
ScreenSpot Pro65.2%estimated ± 10.8 pp, low confidence
SuperGPQA46.0%estimated ± 8.5 pp, low confidence
Toolathlon37.8%estimated ± 8.0 pp, low confidence
Video-MME (w/o subtitle)75.1%estimated ± 1.7 pp, medium confidence
HealthBench Hard0.0%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)5.0%estimated ± 6.5 pp, low confidence
MMLU-Pro (Arcee)77.1%estimated ± 4.0 pp, low confidence
React Native Evals68.2%estimated ± 2.7 pp, low confidence
SWE-Rebench57.0%estimated ± 3.6 pp, low confidence
DAYJOB0.4%estimated ± 6.3 pp, low confidence
DAYJOB Healthcare0.1%estimated ± 6.1 pp, low confidence
Finance Agent v255.1%estimated ± 2.4 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-Verified22.4%estimated ± 7.1 pp, low confidence
BlenderWorld (text-only)70.6%estimated ± 4.0 pp, low confidence
Cookie-Bench74.3%estimated ± 2.5 pp, low confidence
STEMBench2.4%estimated ± 0.2 pp, medium confidence
SimpleQA28.8%estimated ± 4.3 pp, medium confidence
LiveCodeBench61.9%estimated ± 14.6 pp, low confidence
Agents' Last Exam29.6%estimated ± 9.7 pp, low confidence
SEC-Bench Pro18.0%estimated ± 12.3 pp, low confidence
MRCRv265.9%estimated ± 11.3 pp, low confidence
MMLongBench-Doc60.8%estimated ± 2.6 pp, low confidence
BioBasicsBench34.1%estimated ± 3.8 pp, low confidence
LifeVal0.5%estimated ± 5.0 pp, low confidence
MMMU-Pro w/ Python65.8%estimated ± 2.0 pp, medium confidence
ExploitBench Internal Port0.0%estimated ± 1.4 pp, low confidence