benchgap
Alibaba (Qwen) · model

Qwen3.7 Max benchmark scores

As of 2026-11-22, Qwen3.7 Max (Alibaba (Qwen)) has measured scores on 60 benchmarks and estimated scores on 113 more.

BenchmarkScoreSource
AA-GPQA Diamond92.3%measured
AA-HLE40.5%measured
AA-SciCode49.5%measured
AIME2699.2%estimated ± 1.2 pp, low confidence
Artificial Analysis Intelligence Index29.5%measured
CritPt13.4%measured
GDPval-AA31.4%measured
GPQA Diamond92.4%measured
HLE41.4%measured
IFBench79.1%measured
AA-LCR79.0%measured
LiveCodeBench v691.6%measured
AA-Omniscience Accuracy31.1%measured
SciCode53.5%measured
Terminal-Bench 2.178.8%estimated ± 6.7 pp, medium confidence
BrowseComp81.4%estimated ± 5.6 pp, medium confidence
HLE w/ tools53.5%measured
IFEval94.3%measured
LongBench v264.8%estimated ± 5.5 pp, medium confidence
VITA-Bench47.9%measured
τ²-bench results94.7%measured
AA Coding Index66.0%measured
APEX-Agents23.6%estimated ± 9.4 pp, low confidence
APEX-Agents-AA34.9%estimated ± 5.5 pp, medium confidence
BioMysteryBench (human-difficult)45.9%estimated ± 6.8 pp, low confidence
DeepSearchQA86.6%estimated ± 4.5 pp, high confidence
SWE-bench Verified80.4%measured
BFCL v475.0%measured
CyberGym63.9%estimated ± 5.3 pp, low confidence
JobBench48.6%estimated ± 7.9 pp, medium confidence
SkillsBench56.2%estimated ± 9.1 pp, low confidence
SWE-bench Pro60.6%measured
WideResearch78.7%estimated ± 3.3 pp, high confidence
AA Agentic Index23.9%measured
MMLU-Pro89.6%measured
AA-IFBench80.5%measured
BBH100.0%estimated ± 2.8 pp, medium confidence
FailureSensorIQ67.7%estimated ± 1.7 pp, high confidence
GPQA92.4%measured
MMLU90.5%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond90.2%measured
Vals LiveCodeBench87.1%measured
Vals MMLU-Pro89.3%measured
MMMLU90.3%measured
Chess Puzzles27.0%measured
AIME 202599.0%estimated ± 3.8 pp, low confidence
AA MMLU-Pro86.0%estimated ± 0.7 pp, high confidence
Gert Labs44.8%measured
AA-AnalystAgent46.5%estimated ± 3.7 pp, medium confidence
AA EnterpriseOps-Gym45.0%measured
AA Harvey LAB v1.083.1%estimated ± 1.2 pp, medium confidence
AA Tau3 Banking29.7%estimated ± 3.7 pp, high confidence
AA Terminal-Bench 2.180.8%estimated ± 2.5 pp, high confidence
ApprenticeBench5.4%estimated ± 10.4 pp, low confidence
ARC-AGI-192.8%estimated ± 2.5 pp, high confidence
ARC-AGI-270.1%estimated ± 9.7 pp, medium confidence
BabaIsBench25.0%measured
CursorBench 3.142.8%estimated ± 3.4 pp, low confidence
CursorBench 3.258.9%estimated ± 3.6 pp, high confidence
EBR-bench9.5%measured
Terminal-Bench 3.06.3%estimated ± 6.9 pp, low confidence
FrontierCode 1.1 Main28.2%estimated ± 4.2 pp, medium confidence
FrontierMath v2 (Tier 4)34.1%measured
FrontierMath v2 (Tiers 1-3)64.6%measured
FrontierSWE v216.6%estimated ± 8.3 pp, medium confidence
Furniture Assembly24.0%estimated ± 7.4 pp, medium confidence
MaxxBench33.1%estimated ± 4.3 pp, low confidence
MazeBench0.4%estimated ± 2.7 pp, high confidence
Mystery Game Puzzles32.0%measured
NYT Connections85.1%measured
OSWorld-Verified71.5%estimated ± 3.8 pp, medium confidence
Terminal-Bench 4.12.2%estimated ± 9.2 pp, low confidence
Terminal-Bench Hard50.8%measured
Vals SWE-bench68.8%measured
Terminal-Bench 2.1 (Vals AI)61.0%measured
VulcanBench v385.1%estimated ± 5.6 pp, low confidence
CWE-Bench-AA54.7%estimated ± 5.2 pp, medium confidence
AA Cyber Index15.8%estimated ± 9.2 pp, low confidence
DeepsecBench-AA15.0%estimated ± 8.2 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)54.8%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)59.9%estimated ± 0.8 pp, low confidence
AA ITBench42.5%measured
Bug Hunt Bench14.4%estimated ± 7.2 pp, low confidence
CursorBench 4.026.1%estimated ± 2.0 pp, medium confidence
CWE-bench v147.7%estimated ± 5.7 pp, medium confidence
DeepSWE46.6%estimated ± 6.4 pp, low confidence
DRACO76.8%estimated ± 2.0 pp, medium confidence
FrontierCode 2.021.4%estimated ± 6.7 pp, medium confidence
FrontierPhysics2.8%estimated ± 5.0 pp, medium confidence
HLE w/o tools38.6%estimated ± 2.7 pp, high confidence
OSWorld 2.07.3%estimated ± 6.9 pp, low confidence
OSWorld 2.152.2%estimated ± 3.6 pp, medium confidence
OSWorld 2.1 Offline8.8%estimated ± 1.9 pp, low confidence
PostTrainBench v1.114.3%estimated ± 3.7 pp, medium confidence
SpireClimb5.8%estimated ± 7.2 pp, medium confidence
StealthMark37.6%estimated ± 8.9 pp, low confidence
SWE Multilingual78.3%measured
Toolathlon-Verified53.2%estimated ± 2.3 pp, low confidence
VulcanBench Frontier v479.5%estimated ± 4.0 pp, low confidence
AA AutomationBench41.9%estimated ± 7.9 pp, low confidence
GDP.pdf18.3%estimated ± 4.2 pp, high confidence
AA Terminal-Bench 4.010.8%estimated ± 13.7 pp, low confidence
ARC-AGI-30.0%estimated ± 8.3 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, medium confidence
cursorBench4144.8%estimated ± 3.7 pp, medium confidence
CWE-bench43.6%estimated ± 6.2 pp, medium confidence
MKA34.4%estimated ± 4.6 pp, high confidence
SkillsBench official leaderboard (BenchFlow)53.8%estimated ± 6.1 pp, medium confidence
BinaryAudit35.8%estimated ± 12.1 pp, low confidence
CompileBench100.0%estimated ± 10.0 pp, low confidence
OTelBench22.5%estimated ± 6.6 pp, medium confidence
Vibe Code Bench51.2%estimated ± 8.4 pp, medium confidence
FACTS Multimodal47.8%estimated ± 4.0 pp, high confidence
Hermes Bench69.5%estimated ± 1.8 pp, medium confidence
Hermes Index29.4%estimated ± 5.7 pp, low confidence
ExploitBench52.9%estimated ± 7.2 pp, medium confidence
ExploitGym0.8%estimated ± 8.3 pp, low confidence
C-Eval94.4%estimated ± 1.0 pp, low confidence
Claw-Eval65.2%measured
DeepPlanning100.0%estimated ± 9.1 pp, low confidence
HMMT Feb 202697.1%measured
HMMT Nov 202595.2%estimated ± 1.5 pp, low confidence
INCLUDE86.2%measured
MAXIFE89.2%measured
MCP Atlas76.4%measured
MCP-Tasks83.1%estimated ± 6.4 pp, low confidence
MMAnswerBench90.3%estimated ± 2.4 pp, low confidence
MMLU-ProX87.0%measured
MMLU-Redux95.0%measured
NL2Repo47.2%measured
NOVA-6359.0%measured
PolyMath86.5%measured
PostTrainBench v110.5%estimated ± 3.6 pp, medium confidence
QwenClawBench64.3%measured
SuperGPQA73.6%measured
Terminal-Bench 2.069.7%measured
Toolathlon51.8%estimated ± 5.1 pp, low confidence
AA LiveCodeBench86.2%estimated ± 2.6 pp, high confidence
HealthBench Hard32.1%estimated ± 5.1 pp, low confidence
LiveCodeBench Pro84.2%estimated ± 6.0 pp, low confidence
MedXpertQA (Text)61.7%estimated ± 4.5 pp, medium confidence
MMLU-Pro (Arcee)87.7%estimated ± 3.4 pp, low confidence
React Native Evals79.8%estimated ± 2.7 pp, medium confidence
ResearchClawBench18.7%measured
SWE-Rebench61.8%estimated ± 3.6 pp, medium confidence
PostTrainBench11.9%estimated ± 3.7 pp, medium confidence
DAYJOB1.3%estimated ± 3.2 pp, high confidence
DAYJOB Healthcare0.7%estimated ± 4.2 pp, high confidence
Finance Agent v255.5%estimated ± 2.4 pp, medium confidence
BioMysteryBench (human-solvable)86.4%estimated ± 0.6 pp, low confidence
FrontierCode 1.1 Extended56.2%estimated ± 3.0 pp, low confidence
HealthBench (raw)49.2%estimated ± 6.0 pp, medium confidence
HealthBench (length-adjusted)53.8%estimated ± 3.4 pp, medium confidence
HealthBench Professional55.8%estimated ± 4.2 pp, medium confidence
HealthBench Professional (raw)59.8%estimated ± 4.5 pp, high confidence
HLE-Verified49.9%estimated ± 2.0 pp, medium confidence
LABBench282.7%estimated ± 1.8 pp, low confidence
ScarfBench31.9%estimated ± 9.1 pp, low confidence
BlenderWorld (text-only)71.3%estimated ± 2.8 pp, medium confidence
Cookie-Bench80.0%estimated ± 1.3 pp, medium confidence
STEMBench2.4%estimated ± 0.2 pp, medium confidence
SimpleQA33.4%estimated ± 4.3 pp, low confidence
LiveCodeBench79.5%estimated ± 14.6 pp, low confidence
Agents' Last Exam30.6%estimated ± 9.7 pp, medium confidence
OpenHarmony Bench v1.053.4%measured
SEC-Bench Pro21.1%estimated ± 7.5 pp, low confidence
IMOAnswerBench90.0%measured
MRCRv290.4%measured
MMLongBench-Doc61.4%estimated ± 2.6 pp, low confidence
BioBasicsBench30.2%estimated ± 2.2 pp, medium confidence
LifeVal42.3%estimated ± 5.0 pp, low confidence
ExploitBench Internal Port0.1%estimated ± 1.4 pp, low confidence
PinchBench100.0%estimated ± 5.0 pp, low confidence