benchgap
Alibaba (Qwen) · model

Qwen 3.6 Max (preview) benchmark scores

As of 2026-11-22, Qwen 3.6 Max (preview) (Alibaba (Qwen)) has measured scores on 19 benchmarks and estimated scores on 114 more.

BenchmarkScoreSource
AA-GPQA Diamond88.8%measured
AA-HLE30.8%measured
AA-SciCode46.6%estimated ± 3.0 pp, high confidence
Artificial Analysis Intelligence Index28.4%measured
CritPt3.7%measured
GDPval-AA41.0%estimated ± 10.5 pp, low confidence
GPQA Diamond87.9%estimated ± 2.4 pp, high confidence
HLE38.5%estimated ± 5.1 pp, medium confidence
IFBench75.0%estimated ± 6.6 pp, medium confidence
AA-LCR80.7%measured
LiveCodeBench v688.0%estimated ± 1.7 pp, high confidence
AA-Omniscience Accuracy37.9%measured
SciCode47.0%measured
BrowseComp78.4%estimated ± 8.8 pp, medium confidence
HLE w/ tools51.1%estimated ± 5.5 pp, medium confidence
IFEval93.1%estimated ± 2.8 pp, high confidence
LongBench v266.3%estimated ± 5.5 pp, medium confidence
VITA-Bench41.6%estimated ± 8.2 pp, low confidence
τ²-bench results95.9%measured
AA Coding Index61.3%estimated ± 4.3 pp, high confidence
APEX-Agents-AA27.2%estimated ± 9.3 pp, medium confidence
BioMysteryBench (human-difficult)33.6%estimated ± 6.8 pp, low confidence
SWE-bench Verified79.5%estimated ± 2.3 pp, high confidence
BFCL v469.4%estimated ± 8.5 pp, low confidence
CyberGym72.5%estimated ± 11.0 pp, low confidence
JobBench39.6%estimated ± 14.2 pp, low confidence
SWE-bench Pro57.3%measured
WideResearch79.7%estimated ± 3.3 pp, high confidence
AA Agentic Index34.1%estimated ± 9.4 pp, medium confidence
MMLU-Pro85.5%estimated ± 5.0 pp, medium confidence
AA-IFBench76.6%measured
FailureSensorIQ66.9%estimated ± 1.7 pp, high confidence
GPQA89.5%estimated ± 2.4 pp, high confidence
MMLU90.5%estimated ± 0.9 pp, medium confidence
Vals GPQA Diamond87.9%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench85.6%estimated ± 0.8 pp, medium confidence
Vals MMLU-Pro86.9%estimated ± 2.9 pp, high confidence
MMMLU87.9%estimated ± 0.7 pp, medium confidence
Chess Puzzles35.5%estimated ± 4.7 pp, medium confidence
AA MMLU-Pro86.8%estimated ± 0.8 pp, high confidence
Gert Labs47.5%measured
ApprenticeBench6.3%estimated ± 10.4 pp, low confidence
ARC-AGI-177.5%estimated ± 7.8 pp, low confidence
ARC-AGI-237.7%estimated ± 14.4 pp, low confidence
CursorBench 3.152.8%estimated ± 5.6 pp, low confidence
CursorBench 3.254.3%estimated ± 3.6 pp, high confidence
EBR-bench7.8%estimated ± 10.4 pp, low confidence
FrontierCode 1.1 Main38.3%estimated ± 5.0 pp, high confidence
FrontierSWE v210.9%estimated ± 8.3 pp, medium confidence
Furniture Assembly32.9%estimated ± 9.3 pp, medium confidence
MaxxBench47.2%estimated ± 8.8 pp, medium confidence
MazeBench0.5%estimated ± 2.7 pp, high confidence
Mystery Game Puzzles19.0%measured
NYT Connections74.1%measured
OSWorld-Verified73.6%estimated ± 8.6 pp, low confidence
Terminal-Bench 4.12.2%estimated ± 9.2 pp, low confidence
Terminal-Bench Hard43.9%measured
Vals SWE-bench72.8%measured
Terminal-Bench 2.1 (Vals AI)56.2%estimated ± 5.6 pp, medium confidence
CWE-Bench-AA50.8%estimated ± 8.1 pp, medium confidence
AA Cyber Index39.5%estimated ± 12.4 pp, low confidence
DeepsecBench-AA16.2%estimated ± 8.2 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)54.5%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)35.8%estimated ± 0.8 pp, low confidence
AA ITBench43.8%estimated ± 4.6 pp, medium confidence
Bug Hunt Bench11.9%estimated ± 7.2 pp, low confidence
CursorBench 4.033.5%estimated ± 3.3 pp, medium confidence
CWE-bench v149.1%estimated ± 5.7 pp, medium confidence
DeepSWE56.3%estimated ± 7.2 pp, low confidence
FrontierCode 2.020.4%estimated ± 6.7 pp, low confidence
FrontierPhysics2.5%estimated ± 5.0 pp, medium confidence
HLE w/o tools38.6%estimated ± 4.9 pp, high confidence
OSWorld 2.158.1%estimated ± 3.6 pp, high confidence
OSWorld 2.1 Offline56.7%estimated ± 10.1 pp, low confidence
PostTrainBench v1.117.8%estimated ± 3.7 pp, medium confidence
SpireClimb5.8%estimated ± 7.2 pp, medium confidence
StealthMark38.4%estimated ± 9.2 pp, medium confidence
Toolathlon-Verified71.9%estimated ± 3.0 pp, high confidence
VulcanBench Frontier v478.1%estimated ± 8.3 pp, low confidence
AA AutomationBench52.8%estimated ± 9.9 pp, low confidence
GDP.pdf19.1%estimated ± 4.2 pp, high confidence
ARC-AGI-31.3%estimated ± 9.8 pp, medium confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
CWE-bench45.4%estimated ± 6.2 pp, medium confidence
MKA35.0%estimated ± 4.6 pp, high confidence
SkillsBench official leaderboard (BenchFlow)53.3%estimated ± 6.1 pp, medium confidence
BinaryAudit35.8%estimated ± 12.1 pp, low confidence
CompileBench82.2%estimated ± 10.0 pp, low confidence
OTelBench21.6%estimated ± 4.1 pp, medium confidence
FACTS Multimodal42.0%estimated ± 4.0 pp, high confidence
Hermes Index31.1%estimated ± 5.7 pp, low confidence
ExploitBench35.2%estimated ± 7.2 pp, low confidence
ExploitGym3.3%estimated ± 8.3 pp, low confidence
C-Eval94.1%estimated ± 1.0 pp, low confidence
DeepPlanning43.2%estimated ± 11.8 pp, low confidence
MCP Atlas71.1%estimated ± 12.3 pp, low confidence
MMLU-Redux95.7%estimated ± 0.8 pp, medium confidence
NL2Repo42.9%measured
PostTrainBench v115.5%estimated ± 3.6 pp, high confidence
QwenClawBench59.0%measured
SuperGPQA73.9%measured
Terminal-Bench 2.065.4%measured
Toolathlon49.2%estimated ± 8.0 pp, medium confidence
AA LiveCodeBench87.9%estimated ± 2.6 pp, high confidence
HealthBench Hard21.0%estimated ± 8.6 pp, low confidence
LiveCodeBench Pro81.6%estimated ± 6.0 pp, low confidence
MMLU-Pro (Arcee)91.0%estimated ± 4.0 pp, low confidence
React Native Evals78.2%estimated ± 4.7 pp, medium confidence
PostTrainBench15.3%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 v255.6%estimated ± 2.4 pp, medium confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
FrontierCode 1.1 Extended55.1%estimated ± 3.0 pp, low confidence
HealthBench (raw)39.7%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)50.1%estimated ± 3.4 pp, low confidence
HealthBench Professional56.9%estimated ± 4.2 pp, medium confidence
HealthBench Professional (raw)50.9%estimated ± 4.5 pp, medium confidence
HLE-Verified15.6%estimated ± 2.0 pp, low confidence
LABBench275.2%estimated ± 1.8 pp, low confidence
ScarfBench43.7%estimated ± 12.3 pp, low confidence
BlenderWorld (text-only)70.1%estimated ± 2.8 pp, medium confidence
Cookie-Bench77.0%estimated ± 1.3 pp, medium confidence
STEMBench2.5%estimated ± 0.2 pp, medium confidence
SimpleQA42.7%estimated ± 4.3 pp, low confidence
Agents' Last Exam31.0%estimated ± 9.7 pp, medium confidence
OpenHarmony Bench v1.050.8%estimated ± 2.7 pp, high confidence
SEC-Bench Pro41.8%estimated ± 9.3 pp, medium confidence
MRCRv285.8%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.4%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
LifeVal49.7%estimated ± 5.0 pp, low confidence
ExploitBench Internal Port0.1%estimated ± 5.2 pp, low confidence