Codesota · Models · MiMo-V2-ProXiaomi8 results · 2 benchmarks
Model card

MiMo-V2-Pro.

Xiaomiopen-source
§ 01 · Benchmarks

Every benchmark MiMo-V2-Pro has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01SWE-bench VerifiedAgentic AI · SWE-benchresolve-rate78.0%#9/81source ↗
02PLCCNatural Language Processing · Polish Cultural Competencygrammar79.0%#23/165source ↗
03PLCCNatural Language Processing · Polish Cultural Competencygeography89.0%#23/165source ↗
04PLCCNatural Language Processing · Polish Cultural Competencyhistory87.0%#30/165source ↗
05PLCCNatural Language Processing · Polish Cultural Competencyvocabulary73.0%#36/165source ↗
06PLCCNatural Language Processing · Polish Cultural Competencyaverage78.5%#38/165source ↗
07PLCCNatural Language Processing · Polish Cultural Competencyculture-and-tradition79.0%#39/165source ↗
08PLCCNatural Language Processing · Polish Cultural Competencyart-and-entertainment64.0%#50/165source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where MiMo-V2-Pro actually performs.

Agentic AI
1
benchmark
avg rank #9.0
Natural Language Processing
1
benchmark
avg rank #34.1
§ 04 · Related models

Other Xiaomi models scored on Codesota.

MiMo-V2-Flash
1 result
MiMo-V2-Omni
1 result
§ 05 · Sources & freshness

Where these numbers come from.

sdadas/PLCC
7
results
editorial
1
result
8 of 8 rows marked verified.