benchgap
Alibaba (Qwen) · model

Qwen3-Omni-30B-A3B-Thinking benchmark scores

As of 2026-11-22, Qwen3-Omni-30B-A3B-Thinking (Alibaba (Qwen)) has measured scores on 7 benchmarks and estimated scores on 45 more.

BenchmarkScoreSource
AA-GPQA Diamond72.6%measured
AA-HLE7.5%measured
Artificial Analysis Intelligence Index12.6%estimated ± 7.2 pp, medium confidence
CritPt0.0%measured
GDPval-AA0.0%estimated ± 11.0 pp, low confidence
GPQA Diamond71.5%estimated ± 2.4 pp, high confidence
HLE17.5%estimated ± 8.5 pp, medium confidence
IFBench54.6%estimated ± 6.6 pp, medium confidence
AA-LCR0.0%measured
AA-Omniscience Accuracy20.3%estimated ± 7.7 pp, medium confidence
BrowseComp27.4%estimated ± 13.0 pp, low confidence
IFEval89.8%estimated ± 2.8 pp, high confidence
LongBench v251.2%estimated ± 5.5 pp, low confidence
τ²-bench results21.3%measured
AA-MMMU-Pro60.2%measured
APEX-Agents-AA1.6%estimated ± 11.4 pp, low confidence
BioMysteryBench (human-difficult)0.0%estimated ± 6.8 pp, low confidence
BFCL v421.1%estimated ± 8.5 pp, low confidence
AA Agentic Index0.0%estimated ± 12.7 pp, low confidence
MMLU-Pro82.4%estimated ± 7.0 pp, medium confidence
AA-IFBench43.4%measured
GPQA74.7%estimated ± 6.1 pp, medium confidence
MMLU87.9%estimated ± 8.3 pp, medium confidence
Vals GPQA Diamond71.7%estimated ± 3.2 pp, high confidence
Vals MMLU-Pro80.7%estimated ± 3.0 pp, high confidence
MMMLU83.3%estimated ± 0.7 pp, medium confidence
MMMU73.2%estimated ± 2.7 pp, high confidence
AA MMLU-Pro85.7%estimated ± 1.3 pp, medium confidence
ARC-AGI-174.7%estimated ± 7.8 pp, low confidence
ARC-AGI-230.5%estimated ± 14.4 pp, low confidence
ParseBench-146.3%estimated ± 6.2 pp, medium confidence
HLE w/o tools6.0%estimated ± 5.4 pp, low confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
ParseBench-246.3%estimated ± 6.2 pp, medium confidence
CharXiv70.6%estimated ± 6.3 pp, low confidence
AI2D_TEST88.0%estimated ± 2.0 pp, medium confidence
C-Eval90.8%estimated ± 1.1 pp, low confidence
ERQA41.2%estimated ± 3.1 pp, medium confidence
MathVision56.7%estimated ± 3.1 pp, medium confidence
MMLU-Redux88.3%estimated ± 3.3 pp, high confidence
MMMU-Pro61.3%estimated ± 1.5 pp, high confidence
ScreenSpot Pro64.5%estimated ± 10.8 pp, low confidence
Video-MME (w/o subtitle)74.7%estimated ± 1.7 pp, medium confidence
HealthBench Hard0.0%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)3.5%estimated ± 6.5 pp, low confidence
MMLU-Pro (Arcee)77.1%estimated ± 4.0 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
SimpleQA24.9%estimated ± 7.8 pp, medium confidence
MRCRv222.8%estimated ± 11.3 pp, low confidence
BioBasicsBench33.9%estimated ± 10.7 pp, low confidence
MMMU-Pro w/ Python64.9%estimated ± 2.0 pp, medium confidence