benchgap
Alibaba (Qwen) · model

Qwen3.6-35B-A3B benchmark scores

As of 2026-11-22, Qwen3.6-35B-A3B (Alibaba (Qwen)) has measured scores on 54 benchmarks and estimated scores on 136 more.

BenchmarkScoreSource
AA-GPQA Diamond84.1%measured
AA-HLE22.2%measured
AA-SciCode36.6%measured
AIME2692.7%measured
Artificial Analysis Intelligence Index21.6%estimated ± 3.0 pp, high confidence
CritPt0.3%measured
GDPval-AA19.6%measured
GPQA Diamond86.1%estimated ± 1.2 pp, high confidence
HLE21.4%measured
IFBench63.1%estimated ± 6.6 pp, medium confidence
AA-LCR71.7%measured
LiveCodeBench v680.4%measured
AA-Omniscience Accuracy28.3%estimated ± 6.7 pp, low confidence
SciCode36.8%estimated ± 3.1 pp, high confidence
BrowseComp57.4%estimated ± 4.3 pp, medium confidence
HLE w/ tools43.3%estimated ± 5.3 pp, low confidence
IFEval92.5%estimated ± 2.8 pp, high confidence
LongBench v259.5%estimated ± 5.5 pp, medium confidence
VITA-Bench35.6%measured
τ²-bench results95.3%measured
AA Coding Index41.9%measured
AA-MMMU-Pro75.0%measured
APEX-Agents13.7%estimated ± 9.4 pp, low confidence
APEX-Agents-AA25.8%estimated ± 5.5 pp, medium confidence
BioMysteryBench (human-difficult)6.5%estimated ± 6.8 pp, low confidence
DeepSearchQA80.0%estimated ± 4.5 pp, high confidence
SWE-bench Verified73.4%measured
AutomationBench48.4%estimated ± 9.1 pp, low confidence
BFCL v472.0%estimated ± 2.7 pp, high confidence
CyberGym57.1%estimated ± 5.3 pp, low confidence
JobBench21.3%estimated ± 7.3 pp, low confidence
SkillsBench48.6%estimated ± 9.1 pp, low confidence
SWE-bench Pro49.5%measured
τ³-bench results67.2%measured
WideResearch60.1%measured
AA Agentic Index15.0%measured
MMLU-Pro85.2%measured
AA-IFBench64.4%measured
BBH98.9%estimated ± 2.8 pp, medium confidence
FailureSensorIQ64.5%estimated ± 1.7 pp, high confidence
GPQA86.0%measured
MMLU90.7%estimated ± 2.1 pp, medium confidence
Vals GPQA Diamond83.2%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench0.1%estimated ± 3.4 pp, low confidence
Vals MMLU-Pro85.2%estimated ± 2.3 pp, high confidence
MATH-50097.3%estimated ± 3.1 pp, medium confidence
MMMLU85.4%estimated ± 0.7 pp, medium confidence
MMMU81.7%measured
Chess Puzzles37.2%estimated ± 4.7 pp, high confidence
AIME 202594.0%estimated ± 1.8 pp, medium confidence
AA MMLU-Pro86.6%estimated ± 1.2 pp, low confidence
Gert Labs21.5%measured
AA Harvey LAB v1.079.7%estimated ± 1.2 pp, low confidence
AA Tau3 Banking24.6%estimated ± 3.7 pp, medium confidence
ApprenticeBench3.1%estimated ± 10.4 pp, low confidence
ARC-AGI-170.1%estimated ± 6.7 pp, medium confidence
ARC-AGI-227.7%estimated ± 10.9 pp, low confidence
CursorBench 3.147.3%estimated ± 5.6 pp, low confidence
CursorBench 3.239.1%estimated ± 3.6 pp, medium confidence
EBR-bench11.1%estimated ± 10.4 pp, low confidence
FrontierCode 1.1 Main15.8%estimated ± 4.2 pp, low confidence
FrontierMath v2 (Tier 4)0.0%estimated ± 4.0 pp, medium confidence
FrontierMath v2 (Tiers 1-3)20.4%measured
FrontierSWE v20.0%estimated ± 8.3 pp, low confidence
Furniture Assembly33.0%estimated ± 9.3 pp, medium confidence
MaxxBench37.3%estimated ± 5.7 pp, low confidence
MazeBench0.0%estimated ± 2.7 pp, medium confidence
Mystery Game Puzzles22.0%measured
NYT Connections41.6%measured
OfficeQA Pro50.3%estimated ± 6.8 pp, low confidence
OSWorld-Verified72.4%estimated ± 3.8 pp, medium confidence
ParseBench-137.4%measured
Terminal-Bench Hard42.6%estimated ± 4.0 pp, medium confidence
Vals SWE-bench63.1%estimated ± 5.2 pp, low confidence
Terminal-Bench 2.1 (Vals AI)45.2%estimated ± 6.4 pp, medium confidence
CWE-Bench-AA32.7%estimated ± 8.1 pp, low confidence
AA Cyber Index10.4%estimated ± 9.2 pp, low confidence
DeepsecBench-AA6.3%estimated ± 8.2 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)9.3%estimated ± 2.1 pp, low confidence
AA ITBench37.6%estimated ± 4.0 pp, high confidence
Bug Hunt Bench6.5%estimated ± 7.2 pp, low confidence
Chartography (tools)80.3%estimated ± 4.1 pp, low confidence
CursorBench 4.027.6%estimated ± 3.3 pp, medium confidence
CWE-bench v133.9%estimated ± 5.7 pp, low confidence
DeepSWE22.3%estimated ± 7.5 pp, low confidence
DRACO67.4%estimated ± 2.0 pp, low confidence
FrontierCode 2.018.9%estimated ± 6.7 pp, low confidence
FrontierPhysics1.0%estimated ± 4.7 pp, medium confidence
HLE w/o tools22.3%estimated ± 5.3 pp, medium confidence
OSWorld 2.11.8%estimated ± 3.6 pp, medium confidence
PostTrainBench v1.119.7%estimated ± 4.4 pp, medium confidence
SpireClimb5.8%estimated ± 7.2 pp, low confidence
StealthMark20.8%measured
SWE Multilingual67.2%measured
Toolathlon-Verified40.3%estimated ± 2.3 pp, low confidence
VulcanBench Frontier v465.8%estimated ± 6.8 pp, low confidence
AA AutomationBench38.6%estimated ± 9.9 pp, low confidence
GDP.pdf10.2%estimated ± 4.2 pp, medium confidence
ARC-AGI-30.0%estimated ± 9.3 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
CWE-bench26.8%estimated ± 6.2 pp, low confidence
MKA32.8%estimated ± 4.6 pp, medium confidence
SkillsBench official leaderboard (BenchFlow)45.5%estimated ± 6.1 pp, medium confidence
BinaryAudit35.8%estimated ± 12.1 pp, low confidence
CompileBench88.9%estimated ± 10.0 pp, low confidence
OTelBench24.6%estimated ± 4.1 pp, medium confidence
Vibe Code Bench0.7%estimated ± 8.4 pp, medium confidence
FACTS Multimodal24.9%estimated ± 4.0 pp, medium confidence
Hermes Bench50.1%estimated ± 2.9 pp, medium confidence
Hermes Index15.3%estimated ± 5.7 pp, low confidence
ParseBench-245.3%estimated ± 3.5 pp, medium confidence
CharXiv78.0%measured
CharXiv w/o tools79.6%estimated ± 1.2 pp, high confidence
ExploitBench39.6%estimated ± 7.2 pp, medium confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
AI2D_TEST92.7%measured
C-Eval90.0%measured
Claw-Eval68.7%measured
CountBench97.3%estimated ± 1.6 pp, medium confidence
DeepPlanning25.9%measured
DynaMath85.0%estimated ± 0.8 pp, medium confidence
ERQA61.8%estimated ± 2.9 pp, high confidence
HMMT Feb 202590.7%measured
HMMT Feb 202683.6%measured
HMMT Nov 202589.1%measured
INCLUDE82.9%estimated ± 2.0 pp, low confidence
MathVision85.2%estimated ± 2.6 pp, medium confidence
MCP Atlas62.8%measured
MCP-Tasks76.6%estimated ± 0.6 pp, low confidence
MLVU (M-Avg)86.2%measured
MMAnswerBench78.9%measured
MMLU-ProX82.7%estimated ± 1.3 pp, medium confidence
MMLU-Redux93.3%estimated ± 0.6 pp, high confidence
MMMU-Pro75.3%measured
NL2Repo29.4%measured
OmniDocBench 1.589.9%measured
PostTrainBench v114.3%estimated ± 4.6 pp, medium confidence
QwenClawBench52.6%measured
RealWorldQA85.3%measured
ScreenSpot Pro75.1%estimated ± 4.8 pp, medium confidence
SimpleVQA58.9%measured
SuperGPQA64.7%measured
Terminal-Bench 2.051.5%measured
Toolathlon26.9%measured
V*100.0%estimated ± 7.5 pp, medium confidence
Video-MME (w/o subtitle)82.5%measured
Video-MME (with subtitle)86.6%measured
VideoMMMU83.7%measured
We-Math83.2%estimated ± 3.5 pp, medium confidence
AA LiveCodeBench88.1%estimated ± 4.7 pp, low confidence
HealthBench Hard3.5%estimated ± 8.6 pp, low confidence
LiveCodeBench Pro74.9%estimated ± 6.0 pp, low confidence
MedXpertQA (MM)64.0%estimated ± 2.4 pp, high confidence
MMLU-Pro (Arcee)78.3%estimated ± 4.0 pp, low confidence
React Native Evals76.7%estimated ± 2.7 pp, medium confidence
ResearchClawBench18.6%estimated ± 1.3 pp, high confidence
SWE-Rebench57.0%estimated ± 3.6 pp, medium confidence
PostTrainBench18.2%estimated ± 3.7 pp, medium confidence
DAYJOB0.0%estimated ± 3.2 pp, medium confidence
DAYJOB Healthcare0.7%estimated ± 4.2 pp, high confidence
Finance Agent v255.1%estimated ± 2.4 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
FrontierCode 1.1 Extended52.1%estimated ± 3.0 pp, low confidence
HealthBench (raw)30.3%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)46.8%estimated ± 3.4 pp, low confidence
HealthBench Professional58.1%estimated ± 4.5 pp, low confidence
HealthBench Professional (raw)42.1%estimated ± 4.5 pp, medium confidence
ScarfBench24.4%estimated ± 9.1 pp, low confidence
BlenderWorld (text-only)70.2%estimated ± 2.8 pp, medium confidence
Cookie-Bench77.3%estimated ± 1.3 pp, medium confidence
SimpleQA30.7%estimated ± 7.8 pp, low confidence
LiveCodeBench75.2%estimated ± 14.6 pp, low confidence
Agents' Last Exam29.6%estimated ± 9.7 pp, low confidence
BabyVision w/ Python88.8%estimated ± 3.8 pp, low confidence
OpenHarmony Bench v1.051.0%estimated ± 2.4 pp, medium confidence
SEC-Bench Pro22.3%estimated ± 9.3 pp, low confidence
IMOAnswerBench79.7%estimated ± 5.6 pp, medium confidence
BabyVision54.4%estimated ± 9.1 pp, low confidence
MMVU75.5%estimated ± 2.7 pp, medium confidence
PerceptionBench58.2%estimated ± 4.9 pp, low confidence
MRCRv279.5%estimated ± 11.3 pp, low confidence
CC-OCR81.9%measured
MMLongBench-Doc61.0%estimated ± 2.6 pp, low confidence
RefCOCO (avg)92.0%measured
OCRBench V270.3%estimated ± 2.1 pp, medium confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
LifeVal1.0%estimated ± 5.0 pp, low confidence
MMMU-Pro w/ Python78.2%estimated ± 2.0 pp, high confidence
ExploitBench Internal Port0.1%estimated ± 5.2 pp, low confidence
PinchBench94.4%estimated ± 5.5 pp, low confidence