benchgap
Xiaomi · model

MiMo-V2-Pro benchmark scores

As of 2026-11-22, MiMo-V2-Pro (Xiaomi) has measured scores on 13 benchmarks and estimated scores on 93 more.

BenchmarkScoreSource
AA-GPQA Diamond87.0%measured
AA-HLE30.4%measured
AA-SciCode47.5%estimated ± 3.8 pp, high confidence
Artificial Analysis Intelligence Index28.6%measured
CritPt0.3%measured
GDPval-AA30.1%estimated ± 8.0 pp, low confidence
GPQA Diamond87.7%estimated ± 2.4 pp, high confidence
HLE32.6%estimated ± 8.5 pp, medium confidence
IFBench66.8%estimated ± 6.6 pp, medium confidence
AA-LCR68.3%measured
AA-Omniscience Accuracy26.6%measured
SciCode46.7%estimated ± 3.6 pp, high confidence
BrowseComp79.6%estimated ± 5.6 pp, medium confidence
HLE w/ tools50.2%estimated ± 5.5 pp, medium confidence
IFEval92.8%estimated ± 2.8 pp, high confidence
LongBench v257.6%estimated ± 5.5 pp, medium confidence
VITA-Bench35.6%estimated ± 10.7 pp, low confidence
τ²-bench results95.0%measured
AA Coding Index56.8%estimated ± 5.3 pp, medium confidence
APEX-Agents-AA11.6%estimated ± 9.3 pp, medium confidence
BioMysteryBench (human-difficult)6.5%estimated ± 6.8 pp, low confidence
DeepSearchQA77.0%estimated ± 10.2 pp, low confidence
SWE-bench Verified78.0%measured
BFCL v468.9%estimated ± 8.5 pp, low confidence
CyberGym47.3%estimated ± 11.0 pp, low confidence
JobBench24.8%estimated ± 9.3 pp, low confidence
SWE-bench Pro56.3%estimated ± 4.5 pp, high confidence
WideResearch66.6%estimated ± 3.3 pp, high confidence
AA Agentic Index19.3%estimated ± 6.4 pp, medium confidence
MMLU-Pro85.2%estimated ± 5.0 pp, medium confidence
AA-IFBench68.8%measured
FailureSensorIQ63.3%estimated ± 1.7 pp, high confidence
GPQA87.7%estimated ± 6.1 pp, medium confidence
MMLU90.5%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond86.1%estimated ± 3.2 pp, high confidence
Vals LiveCodeBench79.5%estimated ± 10.0 pp, low confidence
Vals MMLU-Pro83.5%estimated ± 2.9 pp, high confidence
MMMLU85.4%estimated ± 0.7 pp, medium confidence
Chess Puzzles19.3%estimated ± 12.3 pp, low confidence
AA MMLU-Pro85.1%estimated ± 0.8 pp, high confidence
Gert Labs24.7%measured
ApprenticeBench3.1%estimated ± 10.4 pp, low confidence
ARC-AGI-175.0%estimated ± 7.8 pp, low confidence
ARC-AGI-231.1%estimated ± 14.4 pp, low confidence
FrontierCode 1.1 Main24.0%estimated ± 4.2 pp, low confidence
MazeBench0.0%estimated ± 2.7 pp, high confidence
Mystery Game Puzzles13.5%estimated ± 14.6 pp, low confidence
NYT Connections25.8%measured
OSWorld-Verified67.9%estimated ± 3.8 pp, medium confidence
Vals SWE-bench73.5%estimated ± 6.6 pp, medium confidence
CWE-Bench-AA35.6%estimated ± 8.1 pp, low confidence
AA Cyber Index9.5%estimated ± 12.4 pp, low confidence
DeepsecBench-AA7.3%estimated ± 8.2 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)54.5%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)61.5%estimated ± 1.1 pp, low confidence
AA ITBench35.9%estimated ± 4.6 pp, low confidence
CWE-bench v136.0%estimated ± 5.7 pp, low confidence
DeepSWE44.2%estimated ± 12.7 pp, low confidence
HLE w/o tools38.8%estimated ± 4.9 pp, high confidence
OSWorld 2.03.2%estimated ± 6.9 pp, low confidence
OSWorld 2.14.0%estimated ± 3.6 pp, medium confidence
StealthMark41.3%estimated ± 10.7 pp, low confidence
Toolathlon-Verified59.2%estimated ± 3.0 pp, high confidence
AA AutomationBench40.3%estimated ± 9.9 pp, low confidence
GDP.pdf11.4%estimated ± 4.2 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
CWE-bench29.3%estimated ± 6.2 pp, low confidence
MKA32.8%estimated ± 4.6 pp, medium confidence
SkillsBench official leaderboard (BenchFlow)37.7%estimated ± 6.1 pp, medium confidence
BinaryAudit9.9%estimated ± 12.1 pp, low confidence
OTelBench6.8%estimated ± 6.6 pp, medium confidence
Vibe Code Bench21.0%estimated ± 8.4 pp, medium confidence
FACTS Multimodal16.6%estimated ± 4.0 pp, medium confidence
Hermes Index17.2%estimated ± 5.7 pp, low confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
C-Eval94.1%estimated ± 1.0 pp, low confidence
Claw-Eval57.8%measured
MCP Atlas54.2%estimated ± 12.9 pp, low confidence
MCP-Tasks69.3%estimated ± 6.4 pp, low confidence
MMLU-Redux94.3%estimated ± 0.8 pp, medium confidence
NL2Repo41.6%estimated ± 6.2 pp, medium confidence
PostTrainBench v116.8%estimated ± 5.5 pp, low confidence
SuperGPQA66.4%estimated ± 9.3 pp, medium confidence
Toolathlon49.7%estimated ± 6.9 pp, medium confidence
HealthBench Hard3.5%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)78.3%estimated ± 4.0 pp, low confidence
React Native Evals78.7%estimated ± 2.7 pp, medium confidence
ResearchClawBench15.3%measured
SWE-Rebench61.3%estimated ± 3.6 pp, medium confidence
Finance Agent v255.1%estimated ± 2.4 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (raw)39.3%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)49.9%estimated ± 3.4 pp, low confidence
HealthBench Professional56.9%estimated ± 4.2 pp, medium confidence
HealthBench Professional (raw)50.5%estimated ± 4.5 pp, medium confidence
HLE-Verified15.3%estimated ± 2.0 pp, low confidence
LABBench272.5%estimated ± 1.8 pp, low confidence
STEMBench2.4%estimated ± 0.2 pp, medium confidence
SimpleQA27.2%estimated ± 4.3 pp, medium confidence
LiveCodeBench78.1%estimated ± 14.6 pp, low confidence
Agents' Last Exam29.6%estimated ± 9.7 pp, low confidence
MRCRv265.9%estimated ± 11.3 pp, low confidence
MMLongBench-Doc60.8%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
LifeVal2.3%estimated ± 5.0 pp, low confidence