benchgap
Alibaba (Qwen) · model

Qwen3.5-122B-A10B benchmark scores

As of 2026-11-22, Qwen3.5-122B-A10B (Alibaba (Qwen)) has measured scores on 30 benchmarks and estimated scores on 140 more.

BenchmarkScoreSource
AA-GPQA Diamond85.7%measured
AA-HLE25.2%measured
AA-SciCode39.7%measured
Artificial Analysis Intelligence Index24.5%estimated ± 3.0 pp, high confidence
CritPt0.6%measured
GDPval-AA15.7%measured
GPQA Diamond86.7%estimated ± 1.2 pp, high confidence
HLE25.1%estimated ± 5.1 pp, medium confidence
IFBench74.0%estimated ± 6.6 pp, medium confidence
AA-LCR76.3%measured
LiveCodeBench v678.9%measured
AA-Omniscience Accuracy29.2%estimated ± 6.7 pp, low confidence
SciCode39.9%estimated ± 3.1 pp, high confidence
BrowseComp63.8%measured
HLE w/ tools41.4%estimated ± 5.3 pp, low confidence
IFEval93.4%measured
LongBench v260.2%measured
VITA-Bench35.4%estimated ± 6.7 pp, low confidence
τ²-bench results93.6%measured
AA Coding Index45.7%measured
AA-MMMU-Pro75.0%measured
APEX-Agents10.7%estimated ± 9.4 pp, low confidence
APEX-Agents-AA12.6%estimated ± 4.4 pp, high confidence
BioMysteryBench (human-difficult)11.6%estimated ± 6.8 pp, low confidence
DeepSearchQA71.8%estimated ± 4.5 pp, medium confidence
SWE-bench Verified72.0%measured
BFCL v470.6%estimated ± 2.7 pp, high confidence
CyberGym53.0%estimated ± 5.3 pp, low confidence
JobBench10.6%estimated ± 8.7 pp, low confidence
SkillsBench36.1%estimated ± 4.1 pp, low confidence
SWE-bench Pro49.6%estimated ± 4.5 pp, high confidence
WideResearch73.3%estimated ± 2.1 pp, low confidence
AA Agentic Index9.6%measured
MMLU-Pro86.7%measured
AA-IFBench75.7%measured
BBH99.8%estimated ± 2.8 pp, medium confidence
FailureSensorIQ65.2%estimated ± 1.7 pp, high confidence
GPQA86.6%measured
MMLU91.3%estimated ± 2.1 pp, medium confidence
Vals GPQA Diamond84.8%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench0.0%estimated ± 3.4 pp, low confidence
Vals MMLU-Pro85.4%estimated ± 2.3 pp, high confidence
MMMLU85.9%estimated ± 0.7 pp, medium confidence
MMMU83.9%measured
Chess Puzzles34.4%estimated ± 4.7 pp, medium confidence
AA MMLU-Pro86.6%estimated ± 1.2 pp, low confidence
Gert Labs28.5%estimated ± 10.0 pp, low confidence
AA Harvey LAB v1.079.4%estimated ± 1.2 pp, low confidence
AA Tau3 Banking25.1%estimated ± 3.6 pp, low confidence
ARC-AGI-172.0%estimated ± 6.7 pp, medium confidence
ARC-AGI-231.5%estimated ± 10.9 pp, low confidence
CursorBench 3.230.9%estimated ± 4.4 pp, medium confidence
EBR-bench5.5%estimated ± 10.4 pp, low confidence
FrontierCode 1.1 Main13.4%estimated ± 4.2 pp, low confidence
FrontierSWE v25.2%estimated ± 14.2 pp, low confidence
Furniture Assembly32.9%estimated ± 9.3 pp, medium confidence
MaxxBench47.2%estimated ± 8.8 pp, medium confidence
MazeBench0.4%estimated ± 5.5 pp, low confidence
Mystery Game Puzzles17.0%measured
NYT Connections51.7%measured
OfficeQA Pro50.3%estimated ± 6.8 pp, low confidence
OSWorld-Verified58.0%measured
ParseBench-159.1%estimated ± 6.2 pp, medium confidence
Terminal-Bench Hard42.2%estimated ± 4.0 pp, medium confidence
Vals SWE-bench67.5%estimated ± 5.5 pp, medium confidence
Terminal-Bench 2.1 (Vals AI)43.2%estimated ± 6.4 pp, medium confidence
CWE-Bench-AA42.6%estimated ± 6.4 pp, medium confidence
AA Cyber Index6.9%estimated ± 9.2 pp, low confidence
DeepsecBench-AA0.1%estimated ± 8.9 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)17.4%estimated ± 2.1 pp, low confidence
AA ITBench35.9%estimated ± 4.0 pp, high confidence
Bug Hunt Bench14.4%estimated ± 10.5 pp, low confidence
Chartography (tools)80.3%estimated ± 4.1 pp, low confidence
CursorBench 4.026.3%estimated ± 4.9 pp, medium confidence
CWE-bench v123.7%estimated ± 6.4 pp, low confidence
DeepSWE31.0%estimated ± 7.5 pp, low confidence
DRACO62.4%estimated ± 2.0 pp, low confidence
FrontierCode 2.026.1%estimated ± 9.3 pp, low confidence
FrontierPhysics2.5%estimated ± 5.0 pp, medium confidence
HLE w/o tools23.8%estimated ± 5.3 pp, medium confidence
OSWorld 2.00.0%estimated ± 3.6 pp, medium confidence
PostTrainBench v1.125.5%estimated ± 7.4 pp, low confidence
SpireClimb5.8%estimated ± 7.2 pp, low confidence
StealthMark37.3%estimated ± 9.2 pp, medium confidence
SWE Multilingual69.9%estimated ± 3.2 pp, low confidence
Toolathlon-Verified29.5%estimated ± 2.3 pp, low confidence
VulcanBench Frontier v469.4%estimated ± 6.8 pp, low confidence
GDP.pdf17.0%estimated ± 4.6 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
SkillsBench official leaderboard (BenchFlow)48.7%estimated ± 6.1 pp, medium confidence
BinaryAudit35.8%estimated ± 12.1 pp, low confidence
CompileBench77.8%estimated ± 10.0 pp, low confidence
OTelBench19.6%estimated ± 4.1 pp, medium confidence
Vibe Code Bench0.2%estimated ± 8.4 pp, medium confidence
FACTS Multimodal30.2%estimated ± 4.0 pp, medium confidence
Hermes Bench44.9%estimated ± 2.9 pp, medium confidence
Hermes Index15.0%estimated ± 8.7 pp, low confidence
ParseBench-267.5%estimated ± 5.0 pp, medium confidence
CharXiv77.2%measured
CharXiv w/o tools81.0%estimated ± 1.2 pp, high confidence
ExploitBench32.1%estimated ± 7.2 pp, low confidence
ExploitGym0.1%estimated ± 10.6 pp, low confidence
AI2D_TEST90.3%estimated ± 0.9 pp, medium confidence
C-Eval91.7%estimated ± 1.0 pp, medium confidence
Claw-Eval55.3%estimated ± 6.2 pp, low confidence
CountBench97.1%estimated ± 1.3 pp, medium confidence
DynaMath84.6%estimated ± 0.8 pp, medium confidence
ERQA63.3%estimated ± 3.1 pp, high confidence
INCLUDE83.2%estimated ± 1.4 pp, low confidence
MathVision86.2%measured
MAXIFE74.8%estimated ± 6.5 pp, low confidence
MCP Atlas64.6%estimated ± 7.8 pp, low confidence
MLVU (M-Avg)85.8%estimated ± 1.5 pp, high confidence
MMLU-ProX82.2%measured
MMLU-Redux94.1%estimated ± 0.6 pp, high confidence
MMMU-Pro76.9%measured
NL2Repo27.7%estimated ± 3.4 pp, medium confidence
NOVA-6356.3%estimated ± 1.3 pp, low confidence
OmniDocBench 1.589.4%estimated ± 2.2 pp, high confidence
PolyMath42.5%estimated ± 11.4 pp, low confidence
PostTrainBench v111.5%estimated ± 5.5 pp, low confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
RealWorldQA82.2%estimated ± 1.5 pp, high confidence
ScreenSpot Pro66.6%estimated ± 6.8 pp, medium confidence
SimpleVQA63.4%estimated ± 7.1 pp, medium confidence
SuperGPQA67.1%measured
Terminal-Bench 2.049.4%measured
Toolathlon34.8%estimated ± 4.2 pp, high confidence
V*93.2%measured
Video-MME (w/o subtitle)83.7%estimated ± 1.2 pp, high confidence
Video-MME (with subtitle)86.6%estimated ± 1.9 pp, high confidence
VideoMMMU84.9%estimated ± 1.5 pp, medium confidence
We-Math87.2%estimated ± 2.1 pp, medium confidence
AA LiveCodeBench88.1%estimated ± 4.7 pp, low confidence
HealthBench Hard6.5%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)67.7%estimated ± 2.4 pp, high confidence
MMLU-Pro (Arcee)79.4%estimated ± 4.0 pp, medium confidence
React Native Evals76.0%estimated ± 2.7 pp, medium confidence
ResearchClawBench11.7%estimated ± 1.9 pp, medium confidence
SWE-Rebench57.0%estimated ± 3.6 pp, medium confidence
DAYJOB1.3%estimated ± 3.2 pp, high confidence
DAYJOB Healthcare0.7%estimated ± 4.2 pp, high confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (raw)33.7%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)48.0%estimated ± 3.4 pp, low confidence
HealthBench Professional58.1%estimated ± 4.5 pp, low confidence
HealthBench Professional (raw)45.3%estimated ± 4.5 pp, medium confidence
ScarfBench24.5%estimated ± 9.1 pp, low confidence
BlenderWorld (text-only)70.0%estimated ± 2.8 pp, medium confidence
Cookie-Bench77.0%estimated ± 1.3 pp, medium confidence
SimpleQA31.5%estimated ± 7.8 pp, low confidence
LiveCodeBench74.3%estimated ± 14.6 pp, low confidence
Agents' Last Exam15.3%estimated ± 11.6 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 Pro40.4%estimated ± 9.3 pp, medium confidence
BabyVision48.5%estimated ± 3.7 pp, high confidence
MMVU74.7%measured
PerceptionBench53.0%estimated ± 3.6 pp, low confidence
ZeroBench15.7%estimated ± 3.6 pp, low confidence
MRCRv284.9%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.2%estimated ± 2.6 pp, low confidence
OCRBench V270.8%estimated ± 3.3 pp, high confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
LifeVal45.3%estimated ± 1.6 pp, low confidence
MMMU-Pro w/ Python78.2%estimated ± 2.0 pp, high confidence
ExploitBench Internal Port0.1%estimated ± 5.2 pp, low confidence
MathVision w/ Python93.0%estimated ± 0.5 pp, low confidence
PinchBench89.1%estimated ± 3.6 pp, medium confidence