benchgap
OpenAI · model

GPT-5.5 Pro benchmark scores

As of 2026-11-22, GPT-5.5 Pro (OpenAI) has measured scores on 9 benchmarks and estimated scores on 76 more.

BenchmarkScoreSource
AA-GPQA Diamond93.6%estimated ± 2.7 pp, high confidence
AA-HLE42.0%estimated ± 4.6 pp, high confidence
AIME2698.1%estimated ± 1.4 pp, medium confidence
Artificial Analysis Intelligence Index33.7%estimated ± 5.6 pp, medium confidence
CritPt30.6%measured
GDPval-AA53.1%estimated ± 7.8 pp, medium confidence
GPQA Diamond93.4%estimated ± 1.4 pp, high confidence
HLE57.2%measured
AA-Omniscience Accuracy53.8%estimated ± 7.4 pp, medium confidence
BrowseComp90.1%measured
HLE w/ tools62.3%estimated ± 5.6 pp, medium confidence
VITA-Bench47.1%estimated ± 6.7 pp, low confidence
τ²-bench results93.6%estimated ± 11.8 pp, low confidence
APEX-Agents-AA41.0%estimated ± 4.4 pp, high confidence
BioMysteryBench (human-difficult)49.8%estimated ± 6.8 pp, low confidence
DeepSearchQA92.2%estimated ± 6.8 pp, low confidence
CyberGym88.2%estimated ± 7.3 pp, medium confidence
JobBench56.4%estimated ± 10.7 pp, low confidence
SkillsBench63.3%estimated ± 4.1 pp, medium confidence
WideResearch82.3%estimated ± 3.5 pp, high confidence
AA Agentic Index49.1%estimated ± 8.2 pp, medium confidence
MMLU-Pro85.7%estimated ± 2.5 pp, low confidence
FailureSensorIQ68.2%estimated ± 2.1 pp, high confidence
GPQA94.4%estimated ± 1.6 pp, high confidence
Vals GPQA Diamond93.2%estimated ± 2.3 pp, high confidence
Vals MMLU-Pro88.5%estimated ± 1.8 pp, high confidence
Chess Puzzles62.0%measured
Gert Labs66.2%estimated ± 11.1 pp, low confidence
AA Harvey LAB v1.092.9%estimated ± 9.8 pp, low confidence
AA Tau3 Banking43.9%estimated ± 3.6 pp, medium confidence
ARC-AGI-195.0%measured
ARC-AGI-284.2%measured
EBR-bench52.8%estimated ± 12.7 pp, low confidence
FrontierMath v2 (Tier 4)78.0%measured
FrontierMath v2 (Tiers 1-3)87.7%measured
Furniture Assembly59.7%estimated ± 14.1 pp, low confidence
MaxxBench66.7%estimated ± 10.3 pp, low confidence
MazeBench8.3%estimated ± 6.4 pp, low confidence
Mystery Game Puzzles57.0%estimated ± 10.3 pp, low confidence
NYT Connections93.0%estimated ± 12.6 pp, low confidence
OSWorld-Verified84.8%estimated ± 5.7 pp, low confidence
CWE-Bench-AA55.3%estimated ± 6.4 pp, medium confidence
AA Cyber Index42.4%estimated ± 13.5 pp, low confidence
DeepsecBench-AA24.6%estimated ± 9.0 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)57.9%estimated ± 4.4 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)70.1%estimated ± 0.8 pp, medium confidence
AA ITBench50.1%estimated ± 4.1 pp, high confidence
DRACO85.9%estimated ± 2.9 pp, medium confidence
FrontierPhysics15.6%estimated ± 6.1 pp, medium confidence
HLE w/o tools43.1%measured
SpireClimb13.6%estimated ± 10.3 pp, low confidence
StealthMark60.6%estimated ± 9.7 pp, low confidence
Toolathlon-Verified74.9%estimated ± 7.4 pp, medium confidence
ARC-AGI-34.9%estimated ± 7.2 pp, medium confidence
SkillsBench official leaderboard (BenchFlow)59.5%estimated ± 6.2 pp, medium confidence
FACTS Multimodal51.6%estimated ± 5.6 pp, medium confidence
ExploitBench84.5%estimated ± 13.4 pp, low confidence
ExploitGym27.8%estimated ± 9.2 pp, low confidence
Claw-Eval80.0%estimated ± 6.4 pp, medium confidence
HMMT Feb 2026100.0%estimated ± 3.1 pp, medium confidence
HMMT Nov 202596.0%estimated ± 1.5 pp, low confidence
MCP Atlas79.5%estimated ± 10.3 pp, low confidence
MMAnswerBench96.2%estimated ± 2.4 pp, low confidence
MMLU-Redux97.0%estimated ± 2.1 pp, medium confidence
SuperGPQA96.0%estimated ± 7.2 pp, low confidence
Toolathlon60.9%estimated ± 4.2 pp, high confidence
HealthBench Hard34.0%estimated ± 8.6 pp, low confidence
MedXpertQA (Text)60.6%estimated ± 8.9 pp, low confidence
ResearchClawBench20.0%estimated ± 2.3 pp, low confidence
DAYJOB11.3%estimated ± 6.3 pp, medium confidence
DAYJOB Healthcare8.3%estimated ± 6.1 pp, low confidence
BioMysteryBench (human-solvable)89.5%estimated ± 0.6 pp, medium confidence
HealthBench (raw)48.7%estimated ± 7.6 pp, low confidence
HealthBench (length-adjusted)57.1%estimated ± 2.5 pp, low confidence
HealthBench Professional52.3%estimated ± 4.2 pp, medium confidence
HLE-Verified52.6%estimated ± 1.3 pp, medium confidence
LABBench280.6%estimated ± 1.7 pp, low confidence
BlenderWorld (text-only)85.7%estimated ± 4.0 pp, medium confidence
Cookie-Bench89.5%estimated ± 2.5 pp, medium confidence
Agents' Last Exam40.7%estimated ± 11.6 pp, low confidence
SEC-Bench Pro71.6%estimated ± 12.3 pp, low confidence
BioBasicsBench34.3%estimated ± 5.1 pp, low confidence
LifeVal79.6%estimated ± 1.6 pp, medium confidence
ExploitBench Internal Port10.0%estimated ± 1.4 pp, medium confidence
PinchBench90.7%estimated ± 3.6 pp, low confidence