Noometry

Model comparison

Gemma 4 31B IT vs MiMo-V2.6-Flash

MiMo-V2.6-Flash is the stronger model overall, scoring 44.4 to 43.2 on the Noometry Index.

Last verified . 13 shared benchmarks.

Gemma 4 31B IT Google

43.2

Rank #85 Confirmed

MiMo-V2.6-Flash Xiaomi

44.4

Rank #74 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Gemma 4 31B IT scores higher in 2 categories and MiMo-V2.6-Flash in 7 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiMo-V2.6-Flash leads 42.0 to 37.9.
  • Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2.6-Flash.
  • MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 262K.

Side by side

Gemma 4 31B ITMiMo-V2.6-Flash
ProviderGoogleXiaomi
Noometry Index43.244.4
Released2026-04-022026-09-22
WeightsOpenOpen
Context window262K1.05M
Max output33K131K
Input $ / M tokens$0.09$0.14
Output $ / M tokens$0.34$0.28
Results tracked3513

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

Category by category

Coding MiMo-V2.6-Flash leads

Gemma 4 31B IT: 41.9 (#98), MiMo-V2.6-Flash: 44.3 (#68)

BenchmarkGemma 4 31B ITMiMo-V2.6-Flash
LMArena Coding14591516
LMArena WebDev1364—
SciCode43.4%—
WeirdML52.3%—
ALE-Bench925.5—

Reasoning MiMo-V2.6-Flash leads

Gemma 4 31B IT: 26.4 (#119), MiMo-V2.6-Flash: 29.6 (#82)

BenchmarkGemma 4 31B ITMiMo-V2.6-Flash
LMArena Hard Prompts14481481
Kagi LLM Benchmark63.5%—
NYT Connections (extended)70.6%—
CritPt1.4%—
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: 41.3 (#72), MiMo-V2.6-Flash: 37.4 (#97)

BenchmarkGemma 4 31B ITMiMo-V2.6-Flash
LMArena Math14641477
OTIS Mock AIME 2024-202573.3%—

Knowledge MiMo-V2.6-Flash leads

Gemma 4 31B IT: 37.9 (#141), MiMo-V2.6-Flash: 42.0 (#91)

BenchmarkGemma 4 31B ITMiMo-V2.6-Flash
LMArena Expert14651516
GPQA Diamond75.8%—
SimpleQA Verified10.4%—
Vectara Hallucination Rate7.4%—

Multimodal Too close to call

Gemma 4 31B IT: 41.0 (#32), MiMo-V2.6-Flash: 40.2 (#39)

BenchmarkGemma 4 31B ITMiMo-V2.6-Flash
LMArena Vision12781266
LMArena Document1425—

Multilingual Too close to call

Gemma 4 31B IT: 54.0 (#52), MiMo-V2.6-Flash: 54.6 (#41)

BenchmarkGemma 4 31B ITMiMo-V2.6-Flash
LMArena Non-English14311439
LMArena Chinese14781501
LMArena Russian14621424
LMArena French1436—
LMArena Spanish1443—

Instruction Following MiMo-V2.6-Flash leads

Gemma 4 31B IT: 75.6 (#58), MiMo-V2.6-Flash: 77.0 (#33)

BenchmarkGemma 4 31B ITMiMo-V2.6-Flash
LMArena Instruction Following14331463

Long Context Too close to call

Gemma 4 31B IT: 44.2 (#67), MiMo-V2.6-Flash: 44.8 (#52)

BenchmarkGemma 4 31B ITMiMo-V2.6-Flash
LMArena Longer Query14461465

Writing & Preference MiMo-V2.6-Flash leads

Gemma 4 31B IT: 60.7 (#92), MiMo-V2.6-Flash: 63.9 (#61)

BenchmarkGemma 4 31B ITMiMo-V2.6-Flash
LMArena Text14431459
LMArena Creative Writing14161408
LMArena Multi-Turn14521460
EQ-Bench Creative Writing1368—
EQ-Bench 41120—

Frequently asked questions

Is Gemma 4 31B IT better than MiMo-V2.6-Flash?

MiMo-V2.6-Flash is the stronger model overall, scoring 44.4 to 43.2 on the Noometry Index.

Which is cheaper, Gemma 4 31B IT or MiMo-V2.6-Flash?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; MiMo-V2.6-Flash lists at $0.14 and $0.28.

Is Gemma 4 31B IT or MiMo-V2.6-Flash better for coding?

MiMo-V2.6-Flash scores higher on coding benchmarks: 44.3 versus 41.9 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2.6-Flash does, with 1.05M tokens against 262K.

How many benchmarks do Gemma 4 31B IT and MiMo-V2.6-Flash share?

13 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and MiMo-V2.6-Flash has 13.

Related comparisons

Go deeper