benchgap
Alibaba (Qwen) · model

Qwen3.5-35B-A3B benchmark scores

As of 2026-11-21, Qwen3.5-35B-A3B (Alibaba (Qwen)) has measured scores on 28 benchmarks and estimated scores on 103 more.

BenchmarkScoreSource
AA-GPQA Diamond84.5%measured
AA-HLE21.0%measured
AA-SciCode43.3%estimated ± 3.8 pp, high confidence
Artificial Analysis Intelligence Index19.3%measured
CritPt0.9%measured
GDPval-AA22.9%estimated ± 7.8 pp, medium confidence
GPQA Diamond84.3%estimated ± 1.2 pp, high confidence
HLE18.1%estimated ± 5.1 pp, medium confidence
IFBench70.5%estimated ± 6.6 pp, medium confidence
AA-LCR72.0%measured
LiveCodeBench v674.6%measured
AA-Omniscience Accuracy20.1%measured
SciCode42.6%estimated ± 3.6 pp, high confidence
BrowseComp61.0%measured
HLE w/ tools43.9%estimated ± 5.5 pp, medium confidence
IFEval91.9%measured
LongBench v259.0%measured
VITA-Bench32.6%estimated ± 6.7 pp, low confidence
τ²-bench results89.2%measured
AA Coding Index38.9%estimated ± 5.3 pp, medium confidence
AA-MMMU-Pro72.7%measured
APEX-Agents-AA11.3%estimated ± 4.4 pp, high confidence
BioMysteryBench (human-difficult)15.7%estimated ± 6.8 pp, low confidence
DeepSearchQA77.0%estimated ± 6.8 pp, low confidence
SWE-bench Verified69.2%measured
BFCL v466.1%estimated ± 8.5 pp, low confidence
CyberGym47.2%estimated ± 7.3 pp, low confidence
JobBench11.6%estimated ± 10.3 pp, low confidence
SkillsBench33.8%estimated ± 4.1 pp, low confidence
SWE-bench Pro46.5%estimated ± 4.5 pp, high confidence
WideResearch73.3%estimated ± 2.1 pp, low confidence
AA Agentic Index7.0%estimated ± 6.8 pp, low confidence
MMLU-Pro85.3%measured
AA-IFBench72.5%measured
BBH99.0%estimated ± 2.8 pp, medium confidence
GPQA84.2%measured
MMLU86.9%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond83.6%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench69.8%estimated ± 10.0 pp, low confidence
Vals MMLU-Pro84.6%estimated ± 2.3 pp, high confidence
MMMLU86.3%estimated ± 0.7 pp, medium confidence
MMMU81.4%measured
AA MMLU-Pro84.1%estimated ± 0.8 pp, medium confidence
Gert Labs29.0%measured
AA Harvey LAB v1.085.7%estimated ± 9.8 pp, low confidence
AA Tau3 Banking23.5%estimated ± 3.6 pp, low confidence
ARC-AGI-164.4%estimated ± 6.7 pp, medium confidence
ARC-AGI-216.3%estimated ± 10.9 pp, low confidence
FrontierCode 1.1 Main8.4%estimated ± 4.2 pp, low confidence
MazeBench0.0%estimated ± 6.4 pp, low confidence
OfficeQA Pro50.3%estimated ± 6.8 pp, low confidence
OSWorld-Verified54.5%measured
ParseBench-156.6%estimated ± 6.2 pp, medium confidence
Terminal-Bench Hard41.4%estimated ± 4.0 pp, medium confidence
Vals SWE-bench61.6%estimated ± 6.6 pp, medium confidence
Terminal-Bench 2.1 (Vals AI)35.1%estimated ± 6.4 pp, medium confidence
CWE-Bench-AA41.1%estimated ± 6.4 pp, medium confidence
AA Cyber Index30.8%estimated ± 13.5 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)51.7%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)54.8%estimated ± 1.1 pp, low confidence
AA ITBench36.0%estimated ± 2.8 pp, medium confidence
Chartography (tools)78.8%estimated ± 4.1 pp, low confidence
DeepSWE27.7%estimated ± 12.7 pp, low confidence
DRACO60.9%estimated ± 2.9 pp, low confidence
HLE w/o tools31.3%estimated ± 4.9 pp, high confidence
OSWorld 2.00.0%estimated ± 3.6 pp, medium confidence
SWE Multilingual68.1%estimated ± 3.2 pp, low confidence
Toolathlon-Verified45.6%estimated ± 7.4 pp, medium confidence
ARC-AGI-31.3%estimated ± 9.8 pp, medium confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
Vibe Code Bench0.0%estimated ± 8.4 pp, medium confidence
ParseBench-265.0%estimated ± 5.0 pp, medium confidence
CharXiv77.5%measured
CharXiv w/o tools79.4%estimated ± 1.2 pp, high confidence
AI2D_TEST91.1%estimated ± 0.9 pp, medium confidence
C-Eval91.4%estimated ± 1.0 pp, medium confidence
Claw-Eval52.9%estimated ± 6.2 pp, low confidence
CountBench93.3%estimated ± 1.3 pp, medium confidence
DynaMath84.8%estimated ± 0.8 pp, medium confidence
ERQA52.9%estimated ± 3.1 pp, high confidence
INCLUDE82.5%estimated ± 1.4 pp, low confidence
MathVision83.9%measured
MAXIFE71.2%estimated ± 6.5 pp, low confidence
MCP Atlas49.4%estimated ± 10.3 pp, low confidence
MLVU (M-Avg)84.8%estimated ± 1.5 pp, high confidence
MMLU-ProX81.0%measured
MMLU-Redux93.3%estimated ± 0.6 pp, high confidence
MMMU-Pro75.1%measured
NL2Repo22.6%estimated ± 3.4 pp, medium confidence
NOVA-6355.7%estimated ± 1.3 pp, low confidence
OmniDocBench 1.588.8%estimated ± 2.2 pp, high confidence
PolyMath39.2%estimated ± 11.4 pp, low confidence
RealWorldQA82.4%estimated ± 1.5 pp, high confidence
ScreenSpot Pro67.1%estimated ± 6.8 pp, medium confidence
SimpleVQA61.4%estimated ± 7.1 pp, medium confidence
SuperGPQA63.4%measured
Terminal-Bench 2.040.5%measured
Toolathlon32.6%estimated ± 4.2 pp, high confidence
V*92.7%measured
Video-MME (w/o subtitle)81.5%estimated ± 1.2 pp, high confidence
Video-MME (with subtitle)85.4%estimated ± 1.9 pp, high confidence
VideoMMMU84.9%estimated ± 1.5 pp, medium confidence
We-Math83.6%estimated ± 2.1 pp, medium confidence
HealthBench Hard8.9%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)63.5%estimated ± 2.4 pp, high confidence
MMLU-Pro (Arcee)80.5%estimated ± 4.0 pp, medium confidence
React Native Evals74.8%estimated ± 2.7 pp, medium confidence
ResearchClawBench13.5%estimated ± 2.1 pp, low confidence
SWE-Rebench53.7%measured
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (raw)28.9%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)46.4%estimated ± 3.4 pp, low confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)40.8%estimated ± 4.5 pp, medium confidence
HLE-Verified15.5%estimated ± 7.1 pp, low confidence
STEMBench2.3%estimated ± 0.2 pp, low confidence
SimpleQA18.2%estimated ± 4.3 pp, medium confidence
LiveCodeBench72.4%estimated ± 14.6 pp, low confidence
Agents' Last Exam14.2%estimated ± 11.6 pp, low confidence
BabyVision w/ Python88.8%estimated ± 3.8 pp, low confidence
BabyVision42.3%estimated ± 3.7 pp, high confidence
MMVU72.3%measured
PerceptionBench50.6%estimated ± 3.6 pp, low confidence
ZeroBench15.7%estimated ± 3.6 pp, low confidence
MRCRv280.1%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.0%estimated ± 2.6 pp, low confidence
OCRBench V270.3%estimated ± 3.3 pp, high confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
LifeVal39.3%estimated ± 1.6 pp, low confidence
MMMU-Pro w/ Python76.2%estimated ± 2.0 pp, high confidence
PinchBench88.9%estimated ± 3.6 pp, medium confidence