benchgap
Xiaomi · model

MiMo-V2-Flash benchmark scores

As of 2026-11-21, MiMo-V2-Flash (Xiaomi) has measured scores on 18 benchmarks and estimated scores on 84 more.

BenchmarkScoreSource
AA-GPQA Diamond65.6%measured
AA-HLE8.6%measured
AA-SciCode44.8%estimated ± 3.4 pp, high confidence
AIME2693.1%estimated ± 4.3 pp, medium confidence
Artificial Analysis Intelligence Index16.1%measured
CritPt0.0%measured
GDPval-AA6.4%measured
GPQA Diamond83.8%estimated ± 1.2 pp, high confidence
HLE22.0%estimated ± 6.5 pp, medium confidence
IFBench54.2%estimated ± 6.6 pp, low confidence
AA-LCR36.3%measured
LiveCodeBench v680.6%measured
AA-Omniscience Accuracy15.6%measured
SciCode44.6%estimated ± 3.6 pp, high confidence
BrowseComp31.7%estimated ± 9.2 pp, low confidence
HLE w/ tools36.9%estimated ± 5.3 pp, low confidence
IFEval88.8%estimated ± 2.8 pp, high confidence
LongBench v260.6%measured
τ²-bench results83.9%measured
AA Coding Index49.8%measured
APEX-Agents4.1%estimated ± 9.4 pp, low confidence
APEX-Agents-AA10.0%estimated ± 9.5 pp, medium confidence
BioMysteryBench (human-difficult)0.0%estimated ± 6.8 pp, low confidence
DeepSearchQA52.9%estimated ± 9.6 pp, medium confidence
SWE-bench Verified73.4%measured
BFCL v464.6%estimated ± 2.7 pp, high confidence
CyberGym16.8%estimated ± 6.0 pp, low confidence
JobBench0.0%estimated ± 8.7 pp, low confidence
SWE-bench Pro51.2%estimated ± 4.5 pp, high confidence
WideResearch45.9%estimated ± 7.8 pp, low confidence
AA Agentic Index4.4%estimated ± 3.1 pp, high confidence
MMLU-Pro84.9%measured
AA-IFBench39.9%measured
AIME 202494.0%estimated ± 2.6 pp, high confidence
BBH98.8%estimated ± 2.8 pp, medium confidence
GPQA83.7%measured
MMLU80.4%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond59.3%measured
Vals LiveCodeBench0.2%estimated ± 3.4 pp, low confidence
Vals MMLU-Pro84.4%estimated ± 2.3 pp, high confidence
MATH-50098.7%estimated ± 2.0 pp, high confidence
MMMLU83.3%estimated ± 0.7 pp, medium confidence
AIME 202594.1%measured
AA MMLU-Pro83.4%estimated ± 0.8 pp, medium confidence
Gert Labs37.0%estimated ± 8.5 pp, medium confidence
AA Tau3 Banking10.7%estimated ± 4.1 pp, medium confidence
ARC-AGI-162.9%estimated ± 6.7 pp, medium confidence
ARC-AGI-213.1%estimated ± 10.9 pp, low confidence
CursorBench 3.147.9%estimated ± 4.8 pp, low confidence
CursorBench 3.234.7%estimated ± 4.4 pp, medium confidence
FrontierCode 1.1 Main15.8%estimated ± 4.2 pp, low confidence
FrontierSWE v23.6%estimated ± 14.3 pp, low confidence
MazeBench0.4%estimated ± 5.5 pp, low confidence
OSWorld-Verified58.8%estimated ± 8.4 pp, low confidence
Vals SWE-bench70.8%estimated ± 5.5 pp, medium confidence
CWE-Bench-AA9.9%estimated ± 10.1 pp, low confidence
DeepsecBench-AA0.0%estimated ± 8.9 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)50.7%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)51.2%estimated ± 1.1 pp, low confidence
AA ITBench35.7%estimated ± 5.1 pp, low confidence
CWE-bench v110.7%estimated ± 6.4 pp, low confidence
DeepSWE35.4%estimated ± 12.7 pp, low confidence
DRACO40.3%estimated ± 2.0 pp, low confidence
HLE w/o tools28.7%estimated ± 4.9 pp, high confidence
SWE Multilingual71.7%measured
Toolathlon-Verified19.3%estimated ± 3.1 pp, medium confidence
GDP.pdf17.0%estimated ± 4.6 pp, medium confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
Vibe Code Bench0.7%estimated ± 8.4 pp, medium confidence
Hermes Bench25.4%estimated ± 2.9 pp, medium confidence
Hermes Index6.4%estimated ± 8.7 pp, low confidence
ExploitGym0.0%estimated ± 10.6 pp, low confidence
C-Eval90.4%estimated ± 1.0 pp, medium confidence
HMMT Feb 202596.2%estimated ± 2.9 pp, high confidence
HMMT Feb 202681.5%estimated ± 11.0 pp, low confidence
INCLUDE84.1%estimated ± 2.0 pp, medium confidence
MCP Atlas56.5%estimated ± 10.7 pp, low confidence
MMLU-ProX83.8%estimated ± 1.3 pp, high confidence
MMLU-Redux93.1%estimated ± 0.6 pp, high confidence
NL2Repo29.9%estimated ± 3.4 pp, high confidence
PostTrainBench v112.6%estimated ± 5.5 pp, low confidence
QwenClawBench55.9%estimated ± 6.0 pp, low confidence
SuperGPQA66.4%estimated ± 8.5 pp, low confidence
Toolathlon27.0%estimated ± 6.3 pp, low confidence
AA LiveCodeBench88.1%estimated ± 4.7 pp, low confidence
HealthBench Hard0.0%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)77.1%estimated ± 4.0 pp, low confidence
React Native Evals76.7%estimated ± 2.7 pp, medium confidence
ResearchClawBench12.4%estimated ± 2.2 pp, low confidence
SWE-Rebench57.0%estimated ± 3.6 pp, medium confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (length-adjusted)54.1%estimated ± 3.7 pp, medium confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
ScarfBench24.6%estimated ± 9.1 pp, low confidence
STEMBench2.3%estimated ± 0.2 pp, low confidence
SimpleQA12.1%estimated ± 4.3 pp, medium confidence
LiveCodeBench75.2%estimated ± 14.6 pp, low confidence
OpenHarmony Bench v1.047.4%estimated ± 2.8 pp, medium confidence
MRCRv222.8%estimated ± 11.3 pp, low confidence
MMLongBench-Doc57.6%estimated ± 2.6 pp, low confidence
BioBasicsBench19.5%estimated ± 10.2 pp, low confidence