Noometry

Model comparison

Gemma 4 31B IT vs MiMo-V2-Flash

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 41.3 on the Noometry Index.

Last verified . 18 shared benchmarks.

Gemma 4 31B IT Google

43.5

Rank #90 Confirmed

MiMo-V2-Flash Xiaomi

41.3

Rank #138 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Gemma 4 31B IT scores higher in 7 categories and MiMo-V2-Flash in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Gemma 4 31B IT leads 42.3 to 36.1.
  • The biggest single-benchmark swing is SciCode: 43.4% for Gemma 4 31B IT and 25.9% for MiMo-V2-Flash.
  • Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2-Flash.

Side by side

Gemma 4 31B ITMiMo-V2-Flash
ProviderGoogleXiaomi
Noometry Index43.541.3
Released2026-04-022025-12-16
WeightsOpenOpen
Context window262K262K
Max output33K66K
Input $ / M tokens$0.09$0.14
Output $ / M tokens$0.34$0.28
Results tracked3521

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Gemma 4 31B IT leads

Gemma 4 31B IT: 42.3 (#108), MiMo-V2-Flash: 36.1 (#211)

BenchmarkGemma 4 31B ITMiMo-V2-Flash
LMArena WebDev13661330
SciCode43.4%25.9%
LMArena Coding14591443
ALE-Bench925.5737.95
WeirdML52.3%—

Reasoning Gemma 4 31B IT leads

Gemma 4 31B IT: 27.2 (#122), MiMo-V2-Flash: 24.9 (#157)

BenchmarkGemma 4 31B ITMiMo-V2-Flash
CritPt1.4%0%
LMArena Hard Prompts14481420
Kagi LLM Benchmark63.5%—
NYT Connections (extended)70.6%—
Chess Puzzles5%—
Thematic Generalization53%—
DTBench82.7%—
LMCA39.3%—
Surface Evolver Bench30.6%—
Epoch Capabilities Index142.74—

Math Gemma 4 31B IT leads

Gemma 4 31B IT: 43.2 (#81), MiMo-V2-Flash: 38.3 (#139)

BenchmarkGemma 4 31B ITMiMo-V2-Flash
LMArena Math14651396
OTIS Mock AIME 2024-202573.3%—

Knowledge MiMo-V2-Flash leads

Gemma 4 31B IT: 37.9 (#151), MiMo-V2-Flash: 39.7 (#131)

BenchmarkGemma 4 31B ITMiMo-V2-Flash
LMArena Expert14651425
GPQA Diamond75.8%—
SimpleQA Verified10.4%—
Vectara Hallucination Rate7.4%—

Multimodal Not comparable

Gemma 4 31B IT: 41.6 (#34), MiMo-V2-Flash: —

BenchmarkGemma 4 31B ITMiMo-V2-Flash
LMArena Vision1277—
LMArena Document1425—

Multilingual Gemma 4 31B IT leads

Gemma 4 31B IT: 53.8 (#57), MiMo-V2-Flash: 51.0 (#113)

BenchmarkGemma 4 31B ITMiMo-V2-Flash
LMArena Non-English14311392
LMArena Chinese14761462
LMArena French14351429
LMArena Russian14601387
LMArena Spanish14441420
LMArena German—1395
LMArena Japanese—1325
LMArena Korean—1358

Instruction Following Gemma 4 31B IT leads

Gemma 4 31B IT: 75.5 (#61), MiMo-V2-Flash: 73.5 (#120)

BenchmarkGemma 4 31B ITMiMo-V2-Flash
LMArena Instruction Following14331392

Long Context Gemma 4 31B IT leads

Gemma 4 31B IT: 44.2 (#71), MiMo-V2-Flash: 43.0 (#110)

BenchmarkGemma 4 31B ITMiMo-V2-Flash
LMArena Longer Query14461409

Writing & Preference Too close to call

Gemma 4 31B IT: 60.5 (#96), MiMo-V2-Flash: 59.7 (#106)

BenchmarkGemma 4 31B ITMiMo-V2-Flash
LMArena Text14431411
LMArena Creative Writing14151375
LMArena Multi-Turn14521404
EQ-Bench Creative Writing1368—
EQ-Bench 41120—

Frequently asked questions

Is Gemma 4 31B IT better than MiMo-V2-Flash?

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 41.3 on the Noometry Index.

Which is cheaper, Gemma 4 31B IT or MiMo-V2-Flash?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; MiMo-V2-Flash lists at $0.14 and $0.28.

Is Gemma 4 31B IT or MiMo-V2-Flash better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 36.1 in the Noometry coding category.

Which has the bigger context window?

Both accept 262K tokens.

How many benchmarks do Gemma 4 31B IT and MiMo-V2-Flash share?

18 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and MiMo-V2-Flash has 21.

Related comparisons

Go deeper