benchgap
OpenAI · model

GPT-5 benchmark scores

As of 2026-11-18, GPT-5 (OpenAI) has measured scores on 24 benchmarks and estimated scores on 122 more.

BenchmarkScoreSource
AA-GPQA Diamond85.4%measured
AA-HLE28.5%measured
AA-SciCode39.3%estimated ± 3.4 pp, high confidence
Artificial Analysis Intelligence Index23.0%measured
CritPt5.7%measured
GDPval-AA20.9%measured
GPQA Diamond88.4%estimated ± 1.8 pp, high confidence
HLE30.5%estimated ± 8.5 pp, medium confidence
IFBench71.1%estimated ± 6.6 pp, medium confidence
AA-LCR78.2%measured
LiveCodeBench v689.1%estimated ± 2.2 pp, medium confidence
AA-Omniscience Accuracy40.3%measured
SciCode48.5%estimated ± 2.9 pp, medium confidence
BrowseComp62.7%estimated ± 6.3 pp, low confidence
HLE w/ tools43.9%estimated ± 5.3 pp, low confidence
IFEval92.9%estimated ± 2.8 pp, high confidence
LongBench v264.2%estimated ± 5.5 pp, medium confidence
τ²-bench results84.8%measured
AA Coding Index37.8%measured
AA-MMMU-Pro74.2%measured
APEX-Agents14.7%estimated ± 9.4 pp, low confidence
APEX-Agents-AA12.3%estimated ± 3.6 pp, low confidence
BioMysteryBench (human-difficult)38.6%estimated ± 6.8 pp, low confidence
DeepSearchQA72.9%estimated ± 8.8 pp, low confidence
SWE-bench Verified76.2%estimated ± 4.4 pp, high confidence
BFCL v472.4%estimated ± 2.7 pp, high confidence
CyberGym45.9%estimated ± 6.0 pp, low confidence
JobBench8.5%measured
SWE-bench Pro54.6%estimated ± 2.9 pp, medium confidence
WideResearch72.2%estimated ± 1.2 pp, low confidence
AA Agentic Index15.6%estimated ± 3.1 pp, high confidence
MMLU-Pro85.7%estimated ± 4.8 pp, high confidence
AA-IFBench73.1%measured
FailureSensorIQ66.1%estimated ± 2.1 pp, high confidence
GPQA87.4%estimated ± 4.5 pp, high confidence
MMLU90.5%estimated ± 0.9 pp, medium confidence
Vals GPQA Diamond85.6%measured
Vals LiveCodeBench85.9%measured
Vals MMLU-Pro86.5%measured
MMMLU88.6%estimated ± 0.7 pp, medium confidence
MMMU82.9%estimated ± 2.7 pp, high confidence
Chess Puzzles36.0%measured
AA MMLU-Pro87.1%measured
Gert Labs50.2%estimated ± 8.4 pp, low confidence
AA EnterpriseOps-Gym34.8%estimated ± 1.2 pp, low confidence
AA Tau3 Banking26.7%estimated ± 4.1 pp, medium confidence
ApprenticeBench0.0%estimated ± 6.0 pp, low confidence
ARC-AGI-179.2%estimated ± 6.5 pp, medium confidence
ARC-AGI-240.1%estimated ± 13.8 pp, low confidence
CursorBench 3.142.8%estimated ± 5.8 pp, low confidence
CursorBench 3.252.2%estimated ± 5.4 pp, low confidence
EBR-bench12.7%measured
FrontierCode 1.1 Main12.9%estimated ± 4.6 pp, medium confidence
FrontierSWE v26.1%estimated ± 9.5 pp, low confidence
Furniture Assembly28.0%estimated ± 6.7 pp, medium confidence
MaxxBench39.3%estimated ± 4.3 pp, low confidence
MazeBench0.0%estimated ± 5.1 pp, low confidence
MirrorCode4.4%measured
Mystery Game Puzzles23.0%measured
NYT Connections79.5%estimated ± 12.6 pp, low confidence
OfficeQA Pro50.3%estimated ± 6.8 pp, low confidence
OSWorld-Verified66.5%estimated ± 8.4 pp, low confidence
ParseBench-158.2%estimated ± 6.2 pp, medium confidence
Vals SWE-bench69.0%measured
VulcanBench v384.2%estimated ± 5.6 pp, low confidence
CWE-Bench-AA28.2%estimated ± 10.1 pp, low confidence
DeepsecBench-AA0.4%estimated ± 8.9 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)52.8%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)44.5%estimated ± 0.8 pp, low confidence
AA ITBench36.3%estimated ± 5.1 pp, low confidence
Chartography (tools)79.7%estimated ± 4.1 pp, low confidence
CursorBench 4.030.8%estimated ± 3.4 pp, medium confidence
CWE-bench v129.9%estimated ± 6.4 pp, low confidence
DeepSWE56.3%estimated ± 7.2 pp, low confidence
DRACO68.8%estimated ± 2.0 pp, low confidence
Epoch Automation Reports11.1%estimated ± 8.4 pp, low confidence
FrontierPhysics2.6%estimated ± 4.2 pp, high confidence
HLE w/o tools35.7%estimated ± 4.9 pp, high confidence
PostTrainBench v1.114.5%estimated ± 3.7 pp, medium confidence
SpireClimb0.0%estimated ± 10.3 pp, low confidence
StealthMark35.8%estimated ± 8.7 pp, low confidence
Toolathlon-Verified46.0%estimated ± 3.1 pp, medium confidence
GDP.pdf16.4%estimated ± 4.1 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)55.3%estimated ± 6.2 pp, medium confidence
CompileBench86.7%measured
OTelBench25.6%estimated ± 4.1 pp, medium confidence
Vibe Code Bench20.1%measured
FACTS Multimodal42.1%estimated ± 5.6 pp, medium confidence
Hermes Bench51.6%estimated ± 2.9 pp, medium confidence
Hermes Index19.5%estimated ± 8.7 pp, low confidence
ParseBench-263.4%estimated ± 6.2 pp, medium confidence
CharXiv80.4%estimated ± 6.3 pp, low confidence
CharXiv w/o tools79.7%estimated ± 2.5 pp, high confidence
ExploitBench0.0%estimated ± 6.4 pp, low confidence
ExploitGym0.3%estimated ± 10.6 pp, low confidence
AI2D_TEST90.4%estimated ± 2.0 pp, medium confidence
C-Eval92.4%estimated ± 1.0 pp, medium confidence
Claw-Eval50.4%estimated ± 4.5 pp, low confidence
CountBench94.4%estimated ± 2.9 pp, medium confidence
DynaMath85.0%estimated ± 3.0 pp, medium confidence
ERQA60.2%estimated ± 3.1 pp, high confidence
MathVision84.2%estimated ± 3.1 pp, high confidence
MCP Atlas22.6%estimated ± 8.9 pp, low confidence
MMLU-Redux96.0%estimated ± 0.8 pp, medium confidence
MMMU-Pro75.5%estimated ± 1.5 pp, high confidence
NL2Repo39.7%estimated ± 4.7 pp, high confidence
PostTrainBench v119.0%estimated ± 3.1 pp, medium confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
RealWorldQA82.5%estimated ± 2.9 pp, medium confidence
ScreenSpot Pro74.0%estimated ± 10.8 pp, low confidence
SuperGPQA81.8%estimated ± 9.3 pp, medium confidence
Toolathlon30.0%estimated ± 6.3 pp, medium confidence
V*100.0%estimated ± 7.5 pp, medium confidence
Video-MME (w/o subtitle)82.5%estimated ± 1.7 pp, medium confidence
Video-MME (with subtitle)84.6%estimated ± 3.7 pp, medium confidence
AA LiveCodeBench84.6%measured
HealthBench Hard24.8%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)70.2%estimated ± 6.5 pp, low confidence
React Native Evals68.6%estimated ± 3.0 pp, low confidence
ResearchClawBench15.1%estimated ± 2.2 pp, medium confidence
SWE-Rebench32.3%estimated ± 6.5 pp, low confidence
PostTrainBench12.1%estimated ± 3.7 pp, medium confidence
DAYJOB1.3%estimated ± 3.2 pp, high confidence
DAYJOB Healthcare0.7%estimated ± 4.2 pp, high confidence
BioMysteryBench (human-solvable)81.8%estimated ± 0.6 pp, low confidence
HealthBench (raw)37.3%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)49.2%estimated ± 3.4 pp, low confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)48.6%estimated ± 4.5 pp, medium confidence
HLE-Verified1.2%estimated ± 4.6 pp, low confidence
LABBench281.2%estimated ± 1.8 pp, low confidence
ScarfBench24.4%estimated ± 9.1 pp, low confidence
BlenderWorld (text-only)70.2%estimated ± 2.8 pp, medium confidence
Cookie-Bench77.4%estimated ± 1.3 pp, medium confidence
STEMBench2.5%estimated ± 0.2 pp, medium confidence
SimpleQA46.0%estimated ± 4.3 pp, low confidence
BabyVision w/ Python87.1%estimated ± 4.0 pp, low confidence
OpenHarmony Bench v1.042.0%estimated ± 2.8 pp, medium confidence
SEC-Bench Pro26.9%estimated ± 7.5 pp, low confidence
MRCRv285.5%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.3%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
MMMU-Pro w/ Python77.5%estimated ± 2.0 pp, high confidence
ExploitBench Internal Port0.2%estimated ± 1.4 pp, medium confidence