benchgap
OpenAI · model

GPT-6.2 Sol benchmark scores

As of 2026-11-18, GPT-6.2 Sol (OpenAI) has measured scores on 25 benchmarks and estimated scores on 72 more.

BenchmarkScoreSource
AA-GPQA Diamond96.2%estimated ± 2.1 pp, low confidence
AA-HLE56.1%estimated ± 3.9 pp, high confidence
AA-SciCode61.4%estimated ± 3.5 pp, medium confidence
Artificial Analysis Intelligence Index57.3%measured
CritPt32.1%estimated ± 4.0 pp, high confidence
GDPval-AA61.7%estimated ± 6.9 pp, low confidence
GPQA Diamond96.0%measured
HLE70.0%estimated ± 2.2 pp, high confidence
AA-Omniscience Accuracy61.6%measured
Terminal-Bench 2.189.1%estimated ± 5.4 pp, low confidence
BrowseComp91.4%estimated ± 2.9 pp, low confidence
HLE w/ tools64.6%estimated ± 5.1 pp, low confidence
AA Coding Index79.0%estimated ± 2.3 pp, low confidence
BioMysteryBench (human-difficult)49.9%estimated ± 7.8 pp, low confidence
AutomationBench47.1%estimated ± 6.1 pp, low confidence
JobBench73.7%estimated ± 11.3 pp, low confidence
SWE-bench Pro85.5%estimated ± 8.4 pp, medium confidence
AA Agentic Index52.5%estimated ± 12.7 pp, low confidence
MMLU-Pro85.5%estimated ± 5.1 pp, low confidence
GPQA96.0%measured
MMLU88.1%estimated ± 4.3 pp, medium confidence
Vals GPQA Diamond98.8%estimated ± 1.2 pp, low confidence
Vals MMLU-Pro89.8%estimated ± 1.6 pp, medium confidence
MMMLU91.6%estimated ± 1.1 pp, low confidence
Chess Puzzles76.8%estimated ± 5.3 pp, low confidence
AA MMLU-Pro90.5%estimated ± 0.8 pp, medium confidence
AA-AnalystAgent53.8%measured
AA EnterpriseOps-Gym28.9%measured
AA Tau3 Banking100.0%estimated ± 2.4 pp, low confidence
ARC-AGI-197.5%measured
ARC-AGI-285.8%measured
CursorBench 3.282.3%estimated ± 4.1 pp, low confidence
EBR-bench89.4%estimated ± 8.6 pp, low confidence
FrontierCode 1.1 Main51.7%estimated ± 3.9 pp, medium confidence
FrontierSWE v260.2%estimated ± 8.3 pp, medium confidence
Furniture Assembly85.1%estimated ± 4.8 pp, medium confidence
MazeBench9.5%estimated ± 6.2 pp, low confidence
MirrorCode68.2%estimated ± 14.2 pp, low confidence
Mystery Game Puzzles87.5%estimated ± 6.4 pp, low confidence
NYT Connections100.0%estimated ± 8.9 pp, low confidence
Terminal-Bench 4.163.2%estimated ± 5.5 pp, medium confidence
Terminal-Bench 2.1 (Vals AI)82.7%estimated ± 6.9 pp, low confidence
CWE-Bench-AA61.7%measured
AA Cyber Index37.7%measured
DeepsecBench-AA51.6%measured
Harvey LAB-AA v1.111.1%measured
HealthBench Professional (length-adjusted, Artificial Analysis)63.3%estimated ± 4.3 pp, medium confidence
HealthBench Professional (raw, Artificial Analysis)70.5%estimated ± 1.1 pp, medium confidence
Bug Hunt Bench47.2%estimated ± 8.9 pp, medium confidence
CursorBench 4.057.4%estimated ± 3.3 pp, high confidence
FrontierCode 2.043.8%measured
FrontierPhysics20.6%estimated ± 2.3 pp, high confidence
HLE w/o tools50.0%estimated ± 4.2 pp, medium confidence
OSWorld 2.067.1%estimated ± 14.7 pp, low confidence
OSWorld 2.1 Offline76.7%estimated ± 7.9 pp, low confidence
PostTrainBench v1.145.7%estimated ± 4.8 pp, high confidence
SpireClimb39.5%estimated ± 2.4 pp, medium confidence
StealthMark68.6%estimated ± 6.1 pp, medium confidence
Terminal-Bench 4.063.3%estimated ± 6.1 pp, medium confidence
Terminal-Bench-Science 0.168.0%measured
Toolathlon-Verified77.9%estimated ± 2.8 pp, low confidence
VulcanBench Frontier v491.6%estimated ± 6.0 pp, low confidence
AA AutomationBench71.3%measured
GDP.pdf30.0%measured
AA Terminal-Bench 4.060.1%measured
ARC-AGI-354.9%measured
ARC-AGI-3 Provider Adapter98.2%measured
CWE-bench64.2%estimated ± 6.2 pp, low confidence
MKA48.3%estimated ± 5.3 pp, medium confidence
FACTS Multimodal52.4%estimated ± 2.7 pp, medium confidence
Hermes Bench100.0%estimated ± 1.8 pp, low confidence
Hermes Index92.4%estimated ± 2.7 pp, low confidence
ExploitBench100.0%measured
ExploitGym30.9%estimated ± 9.8 pp, low confidence
C-Eval93.8%estimated ± 1.2 pp, medium confidence
MMLU-Redux98.6%estimated ± 0.8 pp, low confidence
SuperGPQA83.4%estimated ± 8.5 pp, low confidence
HealthBench Hard34.2%estimated ± 1.2 pp, medium confidence
MedXpertQA (Text)77.7%estimated ± 4.5 pp, low confidence
MMLU-Pro (Arcee)88.8%estimated ± 3.4 pp, low confidence
PostTrainBench41.9%estimated ± 4.6 pp, high confidence
DAYJOB16.6%estimated ± 1.1 pp, medium confidence
DAYJOB Healthcare11.2%estimated ± 1.1 pp, low confidence
HealthBench (raw)54.1%estimated ± 1.6 pp, high confidence
HealthBench (length-adjusted)58.4%estimated ± 0.9 pp, medium confidence
HealthBench Professional65.9%measured
HealthBench Professional (raw)65.5%measured
HLE-Verified54.5%estimated ± 0.7 pp, medium confidence
LABBench284.6%estimated ± 1.7 pp, medium confidence
ScarfBench69.9%estimated ± 5.0 pp, low confidence
STEMBench2.7%estimated ± 0.2 pp, medium confidence
SimpleQA54.1%estimated ± 14.6 pp, low confidence
Agents' Last Exam61.9%estimated ± 11.4 pp, low confidence
SEC-Bench Pro88.3%measured
BioBasicsBench66.8%estimated ± 2.2 pp, medium confidence
LifeVal83.8%measured
ExploitBench Internal Port50.5%measured