benchgap
Xiaomi · model

MiMo-V2-Omni benchmark scores

As of 2026-11-22, MiMo-V2-Omni (Xiaomi) has measured scores on 11 benchmarks and estimated scores on 82 more.

BenchmarkScoreSource
AA-GPQA Diamond82.8%measured
AA-HLE22.1%measured
AA-SciCode46.0%estimated ± 3.8 pp, high confidence
Artificial Analysis Intelligence Index23.9%measured
CritPt1.1%measured
GDPval-AA24.5%estimated ± 11.0 pp, low confidence
GPQA Diamond82.8%estimated ± 2.4 pp, high confidence
HLE24.8%estimated ± 8.5 pp, medium confidence
IFBench57.0%estimated ± 6.6 pp, medium confidence
AA-LCR75.0%measured
AA-Omniscience Accuracy19.3%measured
SciCode45.2%estimated ± 3.6 pp, high confidence
BrowseComp71.4%estimated ± 13.0 pp, low confidence
HLE w/ tools46.2%estimated ± 5.5 pp, medium confidence
IFEval91.6%estimated ± 2.8 pp, high confidence
LongBench v261.7%estimated ± 5.5 pp, medium confidence
VITA-Bench25.6%estimated ± 10.7 pp, low confidence
τ²-bench results91.2%measured
AA Coding Index49.9%estimated ± 5.3 pp, medium confidence
AA-MMMU-Pro69.9%measured
APEX-Agents-AA25.5%estimated ± 11.4 pp, low confidence
BioMysteryBench (human-difficult)18.0%estimated ± 6.8 pp, low confidence
SWE-bench Verified74.8%measured
BFCL v467.1%estimated ± 8.5 pp, low confidence
JobBench3.2%estimated ± 9.3 pp, low confidence
SWE-bench Pro52.7%estimated ± 4.5 pp, high confidence
AA Agentic Index23.4%estimated ± 12.7 pp, low confidence
MMLU-Pro83.3%estimated ± 5.0 pp, medium confidence
AA-IFBench53.5%measured
GPQA83.9%estimated ± 6.1 pp, medium confidence
MMLU84.0%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond81.9%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench76.1%estimated ± 10.0 pp, low confidence
Vals MMLU-Pro77.7%estimated ± 2.9 pp, high confidence
MMMLU86.5%estimated ± 0.7 pp, medium confidence
MMMU80.1%estimated ± 2.7 pp, high confidence
AA MMLU-Pro84.0%estimated ± 0.8 pp, medium confidence
ARC-AGI-175.6%estimated ± 7.8 pp, low confidence
ARC-AGI-232.7%estimated ± 14.4 pp, low confidence
FrontierCode 1.1 Main18.3%estimated ± 4.2 pp, low confidence
OfficeQA Pro50.3%estimated ± 6.8 pp, low confidence
OSWorld-Verified51.2%estimated ± 3.8 pp, low confidence
ParseBench-153.7%estimated ± 6.2 pp, medium confidence
Vals SWE-bench69.2%estimated ± 6.6 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)53.1%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)58.6%estimated ± 1.1 pp, low confidence
Chartography (tools)76.9%estimated ± 4.1 pp, low confidence
DeepSWE38.1%estimated ± 12.7 pp, low confidence
HLE w/o tools35.0%estimated ± 4.9 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
Vibe Code Bench2.1%estimated ± 8.4 pp, medium confidence
ParseBench-257.8%estimated ± 6.2 pp, medium confidence
CharXiv77.5%estimated ± 6.3 pp, low confidence
CharXiv w/o tools76.8%estimated ± 2.5 pp, medium confidence
AI2D_TEST88.1%estimated ± 2.0 pp, medium confidence
C-Eval92.7%estimated ± 1.0 pp, medium confidence
Claw-Eval45.2%measured
CountBench91.4%estimated ± 2.9 pp, low confidence
DynaMath69.4%estimated ± 3.0 pp, low confidence
ERQA43.6%estimated ± 3.1 pp, medium confidence
MathVision77.7%estimated ± 3.1 pp, high confidence
MCP Atlas27.9%estimated ± 13.5 pp, low confidence
MCP-Tasks48.7%estimated ± 6.4 pp, low confidence
MMLU-Redux93.4%estimated ± 0.8 pp, low confidence
MMMU-Pro71.3%estimated ± 1.5 pp, high confidence
NL2Repo35.0%estimated ± 6.2 pp, medium confidence
PostTrainBench v113.7%estimated ± 5.5 pp, low confidence
RealWorldQA79.6%estimated ± 2.9 pp, low confidence
ScreenSpot Pro71.2%estimated ± 10.8 pp, low confidence
SuperGPQA64.7%estimated ± 9.3 pp, low confidence
V*48.3%estimated ± 7.5 pp, low confidence
Video-MME (w/o subtitle)79.7%estimated ± 1.7 pp, medium confidence
Video-MME (with subtitle)81.7%estimated ± 3.7 pp, low confidence
HealthBench Hard10.4%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)50.2%estimated ± 6.5 pp, low confidence
MMLU-Pro (Arcee)81.3%estimated ± 4.0 pp, medium confidence
React Native Evals77.3%estimated ± 2.7 pp, medium confidence
ResearchClawBench12.6%estimated ± 1.3 pp, medium confidence
SWE-Rebench57.1%estimated ± 3.6 pp, medium confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (raw)30.2%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)46.8%estimated ± 3.4 pp, low confidence
HealthBench Professional56.8%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)42.0%estimated ± 4.5 pp, medium confidence
STEMBench2.3%estimated ± 0.2 pp, low confidence
SimpleQA17.1%estimated ± 4.3 pp, medium confidence
LiveCodeBench76.1%estimated ± 14.6 pp, low confidence
BabyVision w/ Python84.2%estimated ± 4.0 pp, low confidence
MRCRv284.2%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.2%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
MMMU-Pro w/ Python73.6%estimated ± 2.0 pp, high confidence