benchgap
OpenAI · model

GPT-5.5 benchmark scores

As of 2026-11-22, GPT-5.5 (OpenAI) has measured scores on 76 benchmarks and estimated scores on 121 more.

BenchmarkScoreSource
AA-GPQA Diamond93.5%measured
AA-HLE45.8%measured
AA-SciCode55.8%measured
AIME2698.0%estimated ± 1.4 pp, medium confidence
Artificial Analysis Intelligence Index38.4%measured
CritPt27.1%measured
GDPval-AA42.5%measured
GPQA Diamond93.6%measured
HLE52.2%measured
IFBench74.2%estimated ± 6.6 pp, medium confidence
AA-LCR84.3%measured
LiveCodeBench v688.8%estimated ± 2.2 pp, medium confidence
AA-Omniscience Accuracy58.0%measured
SciCode47.3%estimated ± 2.9 pp, medium confidence
Terminal-Bench 2.186.2%estimated ± 6.7 pp, medium confidence
BrowseComp84.4%measured
HLE w/ tools57.0%estimated ± 4.1 pp, low confidence
IFEval93.0%estimated ± 2.8 pp, high confidence
LongBench v269.6%estimated ± 5.5 pp, low confidence
VITA-Bench46.0%estimated ± 6.7 pp, low confidence
τ²-bench results98.0%measured
AA Coding Index74.9%measured
AA-MMMU-Pro79.9%measured
APEX-Agents36.6%estimated ± 4.9 pp, low confidence
APEX-Agents-AA37.7%measured
BioMysteryBench (human-difficult)49.3%estimated ± 6.8 pp, low confidence
DeepSearchQA91.1%estimated ± 4.5 pp, high confidence
SWE-bench Verified88.7%estimated ± 2.2 pp, medium confidence
AutomationBench25.7%estimated ± 7.1 pp, low confidence
BFCL v476.0%estimated ± 2.7 pp, medium confidence
CyberGym81.8%measured
JobBench42.7%measured
SkillsBench56.3%estimated ± 4.1 pp, medium confidence
SWE-bench Pro58.6%measured
WideResearch79.7%estimated ± 1.2 pp, medium confidence
AA Agentic Index37.3%measured
MMLU-Pro85.6%estimated ± 2.5 pp, low confidence
AA-IFBench75.9%measured
FailureSensorIQ68.5%estimated ± 1.7 pp, high confidence
GPQA93.6%measured
MMLU94.8%estimated ± 1.2 pp, medium confidence
Vals GPQA Diamond93.2%measured
Vals LiveCodeBench85.3%measured
Vals MMLU-Pro88.1%measured
MMMLU90.9%estimated ± 1.1 pp, low confidence
MMMU86.4%estimated ± 0.8 pp, medium confidence
Chess Puzzles63.0%measured
AA MMLU-Pro90.0%estimated ± 0.7 pp, medium confidence
Gert Labs66.4%measured
AA-AnalystAgent50.0%measured
AA EnterpriseOps-Gym46.6%measured
AA Harvey LAB v1.091.4%estimated ± 1.2 pp, medium confidence
AA Tau3 Banking39.0%measured
AA Terminal-Bench 2.184.3%measured
ApprenticeBench20.0%measured
ARC-AGI-195.0%measured
ARC-AGI-285.0%measured
BabaIsBench100.0%measured
CursorBench 3.159.2%measured
CursorBench 3.258.4%measured
EBR-bench34.3%measured
Terminal-Bench 3.021.0%estimated ± 6.9 pp, medium confidence
FrontierCode 1.1 Main43.0%measured
FrontierMath v2 (Tier 4)72.5%measured
FrontierMath v2 (Tiers 1-3)85.3%measured
FrontierSWE v237.6%estimated ± 8.0 pp, medium confidence
Furniture Assembly44.2%measured
MaxxBench61.1%estimated ± 4.3 pp, low confidence
MazeBench0.0%measured
MirrorCode23.3%measured
Mystery Game Puzzles56.0%measured
NYT Connections96.2%measured
OfficeQA Pro54.1%measured
OSWorld-Verified78.7%measured
ParseBench-166.4%measured
Terminal-Bench 4.141.4%estimated ± 9.2 pp, low confidence
Terminal-Bench Hard60.6%measured
Vals SWE-bench82.6%measured
Terminal-Bench 2.1 (Vals AI)76.4%measured
VulcanBench v379.6%estimated ± 5.1 pp, low confidence
CWE-Bench-AA44.7%estimated ± 4.5 pp, medium confidence
AA Cyber Index23.1%estimated ± 9.2 pp, low confidence
DeepsecBench-AA25.8%estimated ± 8.2 pp, medium confidence
Harvey LAB-AA v1.17.4%estimated ± 4.0 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)57.5%estimated ± 4.3 pp, medium confidence
HealthBench Professional (raw, Artificial Analysis)68.9%estimated ± 0.8 pp, medium confidence
AA ITBench45.8%measured
Bug Hunt Bench14.3%estimated ± 6.3 pp, low confidence
Chartography (tools)83.3%estimated ± 4.1 pp, low confidence
CursorBench 4.039.9%estimated ± 2.0 pp, high confidence
CWE-bench v152.7%estimated ± 4.5 pp, low confidence
DeepSWE60.7%estimated ± 4.3 pp, high confidence
DRACO86.9%estimated ± 0.7 pp, low confidence
FrontierCode 2.023.6%measured
FrontierPhysics4.0%estimated ± 4.4 pp, high confidence
HLE w/o tools41.4%measured
OSWorld 2.013.0%measured
OSWorld 2.176.1%estimated ± 3.6 pp, high confidence
OSWorld 2.1 Offline36.7%estimated ± 1.9 pp, low confidence
PostTrainBench v1.127.2%measured
ProgramBench0.0%estimated ± 4.8 pp, low confidence
SpireClimb1.1%estimated ± 5.4 pp, low confidence
StealthMark36.5%measured
SWE-bench Multimodal54.9%estimated ± 5.6 pp, low confidence
Toolathlon-Verified68.8%estimated ± 1.0 pp, low confidence
VulcanBench Frontier v478.5%measured
AA AutomationBench58.0%estimated ± 4.8 pp, medium confidence
GDP.pdf16.4%estimated ± 4.1 pp, medium confidence
AA Terminal-Bench 4.040.3%estimated ± 13.7 pp, low confidence
ARC-AGI-30.4%measured
ARC-AGI-3 Provider Adapter2.2%estimated ± 4.1 pp, high confidence
cursorBench4144.8%estimated ± 3.7 pp, high confidence
CWE-bench61.1%estimated ± 4.6 pp, high confidence
MKA36.9%estimated ± 3.1 pp, high confidence
SkillsBench official leaderboard (BenchFlow)67.3%measured
BinaryAudit55.0%estimated ± 12.0 pp, low confidence
OTelBench22.5%estimated ± 6.6 pp, low confidence
Vibe Code Bench69.8%measured
FACTS Multimodal39.5%estimated ± 3.0 pp, high confidence
Hermes Bench71.4%estimated ± 1.5 pp, medium confidence
Hermes Index37.2%estimated ± 3.1 pp, high confidence
ParseBench-272.0%estimated ± 3.5 pp, high confidence
CharXiv86.9%estimated ± 5.1 pp, low confidence
CharXiv w/o tools85.5%estimated ± 1.2 pp, high confidence
ExploitBench35.0%estimated ± 1.9 pp, medium confidence
ExploitGym13.4%measured
AI2D_TEST94.1%estimated ± 2.0 pp, medium confidence
C-Eval97.0%estimated ± 1.0 pp, low confidence
Claw-Eval61.0%estimated ± 3.2 pp, high confidence
CountBench98.1%estimated ± 2.9 pp, medium confidence
DeepPlanning47.8%estimated ± 13.1 pp, low confidence
DynaMath85.5%estimated ± 3.0 pp, medium confidence
ERQA68.7%estimated ± 3.1 pp, high confidence
HMMT Feb 2026100.0%estimated ± 3.1 pp, medium confidence
HMMT Nov 202596.0%estimated ± 1.5 pp, low confidence
MathVision90.9%estimated ± 3.0 pp, high confidence
MCP Atlas75.3%measured
MCP-Tasks79.3%estimated ± 7.0 pp, low confidence
MLVU (M-Avg)87.4%estimated ± 2.2 pp, high confidence
MMAnswerBench95.6%estimated ± 2.4 pp, low confidence
MMLU-Redux98.2%estimated ± 0.8 pp, low confidence
MMMU-Pro81.2%measured
NL2Repo47.4%estimated ± 4.7 pp, high confidence
PostTrainBench v125.0%measured
QwenClawBench62.6%estimated ± 2.6 pp, high confidence
RealWorldQA84.3%estimated ± 2.8 pp, high confidence
ScreenSpot Pro77.2%estimated ± 9.6 pp, low confidence
SimpleVQA70.1%estimated ± 7.5 pp, medium confidence
SuperGPQA91.3%estimated ± 7.2 pp, medium confidence
Terminal-Bench 2.082.0%measured
Toolathlon55.6%measured
V*100.0%estimated ± 7.5 pp, medium confidence
Video-MME (w/o subtitle)86.1%estimated ± 1.3 pp, medium confidence
Video-MME (with subtitle)88.2%estimated ± 3.0 pp, high confidence
VideoMMMU87.2%estimated ± 2.4 pp, high confidence
We-Math83.6%estimated ± 7.4 pp, low confidence
AA LiveCodeBench93.1%estimated ± 2.6 pp, medium confidence
HealthBench Hard36.1%estimated ± 5.1 pp, low confidence
LiveCodeBench Pro82.6%estimated ± 6.0 pp, low confidence
MedXpertQA (MM)77.1%estimated ± 2.4 pp, high confidence
MedXpertQA (Text)66.3%estimated ± 4.5 pp, medium confidence
MMLU-Pro (Arcee)88.1%estimated ± 3.4 pp, low confidence
React Native Evals84.7%measured
ResearchClawBench17.0%measured
SWE-Rebench62.2%estimated ± 6.5 pp, low confidence
PostTrainBench23.9%measured
DAYJOB1.4%measured
DAYJOB Healthcare0.0%measured
Finance Agent v258.8%estimated ± 2.4 pp, medium confidence
BioMysteryBench (human-solvable)89.5%estimated ± 0.6 pp, medium confidence
FrontierCode 1.1 Extended55.1%estimated ± 1.6 pp, low confidence
HealthBench (raw)53.9%estimated ± 6.0 pp, medium confidence
HealthBench (length-adjusted)53.8%estimated ± 0.9 pp, medium confidence
HealthBench Professional56.8%estimated ± 3.6 pp, high confidence
HealthBench Professional (raw)64.2%estimated ± 4.5 pp, high confidence
HLE-Verified52.9%estimated ± 1.3 pp, medium confidence
LABBench280.6%estimated ± 1.7 pp, low confidence
ScarfBench69.9%estimated ± 5.0 pp, low confidence
BlenderWorld (text-only)81.9%estimated ± 2.8 pp, medium confidence
Cookie-Bench89.4%estimated ± 1.3 pp, medium confidence
STEMBench2.7%estimated ± 0.2 pp, medium confidence
SimpleQA35.4%estimated ± 7.8 pp, low confidence
Agents' Last Exam27.5%estimated ± 3.3 pp, medium confidence
BabyVision w/ Python89.3%estimated ± 3.8 pp, low confidence
OpenHarmony Bench v1.058.9%estimated ± 2.4 pp, high confidence
SEC-Bench Pro45.8%measured
BabyVision67.9%estimated ± 9.1 pp, low confidence
MMVU79.1%estimated ± 2.7 pp, medium confidence
PerceptionBench61.3%estimated ± 4.9 pp, low confidence
MRCRv286.0%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.6%estimated ± 2.6 pp, low confidence
OCRBench V271.9%estimated ± 3.3 pp, high confidence
BioBasicsBench35.4%measured
LifeVal77.4%measured
MMMU-Pro w/ Python83.2%measured
ExploitBench Internal Port11.4%estimated ± 1.4 pp, medium confidence
PinchBench90.4%estimated ± 3.6 pp, low confidence