Noometry

Model comparison

Gemma 3 4B vs MiMo-V2-Omni

MiMo-V2-Omni is the stronger model overall, scoring 43.6 to 28.1 on the Noometry Index. Gemma 3 4B costs 3.5× less per token, which makes it the better buy when MiMo-V2-Omni's lead doesn't matter for your workload.

Last verified . 12 shared benchmarks.

Gemma 3 4B Google

28.1

Rank #326 Confirmed

MiMo-V2-Omni Xiaomi

43.6

Rank #88 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and MiMo-V2-Omni in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiMo-V2-Omni leads 40.5 to 11.8.
  • Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2-Omni.
  • MiMo-V2-Omni accepts more context: 262K tokens versus 131K.
  • Gemma 3 4B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 4BMiMo-V2-Omni
ProviderGoogleXiaomi
Noometry Index28.143.6
Released2025-03-122026-03-18
WeightsOpenProprietary
Context window131K262K
Max output4K131K
Input $ / M tokens$0.04$0.14
Output $ / M tokens$0.08$0.28
Results tracked2218

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

Category by category

Coding MiMo-V2-Omni leads

Gemma 3 4B: 35.9 (#215), MiMo-V2-Omni: 43.3 (#89)

BenchmarkGemma 3 4BMiMo-V2-Omni
LMArena Coding12301466

Agentic & Tool Use Not comparable

Gemma 3 4B: 20.9 (#142), MiMo-V2-Omni: —

BenchmarkGemma 3 4BMiMo-V2-Omni
Berkeley Function Calling Leaderboard19.6%—

Reasoning MiMo-V2-Omni leads

Gemma 3 4B: 13.2 (#335), MiMo-V2-Omni: 29.7 (#88)

BenchmarkGemma 3 4BMiMo-V2-Omni
LMArena Hard Prompts12531445
Kagi LLM Benchmark25.2%—
Chess Puzzles0%—
DTBench50.9%—
LMCA2.8%—
Epoch Capabilities Index116.02—

Math MiMo-V2-Omni leads

Gemma 3 4B: 16.8 (#292), MiMo-V2-Omni: 39.1 (#115)

BenchmarkGemma 3 4BMiMo-V2-Omni
LMArena Math12391430
OTIS Mock AIME 2024-20257.5%—

Knowledge MiMo-V2-Omni leads

Gemma 3 4B: 11.8 (#299), MiMo-V2-Omni: 40.5 (#118)

BenchmarkGemma 3 4BMiMo-V2-Omni
LMArena Expert12231449
GPQA Diamond23.2%—
Vectara Hallucination Rate6.4%—

Multimodal Not comparable

Gemma 3 4B: —, MiMo-V2-Omni: 38.6 (#63)

BenchmarkGemma 3 4BMiMo-V2-Omni
LMArena Vision—1228

Multilingual MiMo-V2-Omni leads

Gemma 3 4B: 42.5 (#194), MiMo-V2-Omni: 51.8 (#102)

BenchmarkGemma 3 4BMiMo-V2-Omni
LMArena Non-English12731404
LMArena German12811399
LMArena Russian12941412
LMArena Chinese—1465
LMArena French—1447
LMArena Japanese—1317
LMArena Korean—1355
LMArena Spanish—1434

Instruction Following MiMo-V2-Omni leads

Gemma 3 4B: 65.2 (#225), MiMo-V2-Omni: 75.2 (#66)

BenchmarkGemma 3 4BMiMo-V2-Omni
LMArena Instruction Following12391428

Long Context MiMo-V2-Omni leads

Gemma 3 4B: 38.7 (#194), MiMo-V2-Omni: 44.1 (#76)

BenchmarkGemma 3 4BMiMo-V2-Omni
LMArena Longer Query12731442

Writing & Preference MiMo-V2-Omni leads

Gemma 3 4B: 42.0 (#239), MiMo-V2-Omni: 61.4 (#87)

BenchmarkGemma 3 4BMiMo-V2-Omni
LMArena Text12911423
LMArena Creative Writing12711392
LMArena Multi-Turn12551445
EQ-Bench Creative Writing1068—

Frequently asked questions

Is Gemma 3 4B better than MiMo-V2-Omni?

MiMo-V2-Omni is the stronger model overall, scoring 43.6 to 28.1 on the Noometry Index. Gemma 3 4B costs 3.5× less per token, which makes it the better buy when MiMo-V2-Omni's lead doesn't matter for your workload.

Which is cheaper, Gemma 3 4B or MiMo-V2-Omni?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; MiMo-V2-Omni lists at $0.14 and $0.28.

Is Gemma 3 4B or MiMo-V2-Omni better for coding?

MiMo-V2-Omni scores higher on coding benchmarks: 43.3 versus 35.9 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2-Omni does, with 262K tokens against 131K.

How many benchmarks do Gemma 3 4B and MiMo-V2-Omni share?

12 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and MiMo-V2-Omni has 18.

Related comparisons

Go deeper