# Gemma 3 4B vs MiMo-V2-Flash

> MiMo-V2-Flash is the stronger model overall, scoring 41.3 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-Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-4b-vs-mimo-v2-flash
- Last updated: 2026-10-11
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and MiMo-V2-Flash in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiMo-V2-Flash leads 39.7 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-Flash.
- MiMo-V2-Flash accepts more context: 262K tokens versus 131K.

## Snapshot

| | Gemma 3 4B | MiMo-V2-Flash |
|---|---|---|
| Provider | Google | Xiaomi |
| Noometry Index | 28.1 | 41.3 |
| Rank | 326 | 138 |
| Context | 131K | 262K |
| Input $/M | $0.04 | $0.14 |
| Output $/M | $0.08 | $0.28 |
| Weights | Open | Open |

## Coding

- Gemma 3 4B: 35.9 (#215)
- MiMo-V2-Flash: 36.1 (#211)

| Benchmark | Gemma 3 4B | MiMo-V2-Flash |
|---|---|---|
| LMArena Coding | 1230 | 1443 |
| LMArena WebDev | — | 1330 |
| SciCode | — | 25.9% |
| ALE-Bench | — | 737.95 |

## Agentic & Tool Use

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

| Benchmark | Gemma 3 4B | MiMo-V2-Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |

## Reasoning

- Gemma 3 4B: 13.2 (#335)
- MiMo-V2-Flash: 24.9 (#157)

| Benchmark | Gemma 3 4B | MiMo-V2-Flash |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1420 |
| Kagi LLM Benchmark | 25.2% | — |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |

## Math

- Gemma 3 4B: 16.8 (#292)
- MiMo-V2-Flash: 38.3 (#139)

| Benchmark | Gemma 3 4B | MiMo-V2-Flash |
|---|---|---|
| LMArena Math | 1239 | 1396 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |

## Knowledge

- Gemma 3 4B: 11.8 (#299)
- MiMo-V2-Flash: 39.7 (#131)

| Benchmark | Gemma 3 4B | MiMo-V2-Flash |
|---|---|---|
| LMArena Expert | 1223 | 1425 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |

## Multilingual

- Gemma 3 4B: 42.5 (#194)
- MiMo-V2-Flash: 51.0 (#113)

| Benchmark | Gemma 3 4B | MiMo-V2-Flash |
|---|---|---|
| LMArena Non-English | 1273 | 1392 |
| LMArena German | 1281 | 1395 |
| LMArena Russian | 1294 | 1387 |
| LMArena Chinese | — | 1462 |
| LMArena French | — | 1429 |
| LMArena Japanese | — | 1325 |
| LMArena Korean | — | 1358 |
| LMArena Spanish | — | 1420 |

## Instruction Following

- Gemma 3 4B: 65.2 (#225)
- MiMo-V2-Flash: 73.5 (#120)

| Benchmark | Gemma 3 4B | MiMo-V2-Flash |
|---|---|---|
| LMArena Instruction Following | 1239 | 1392 |

## Long Context

- Gemma 3 4B: 38.7 (#194)
- MiMo-V2-Flash: 43.0 (#110)

| Benchmark | Gemma 3 4B | MiMo-V2-Flash |
|---|---|---|
| LMArena Longer Query | 1273 | 1409 |

## Writing & Preference

- Gemma 3 4B: 42.0 (#239)
- MiMo-V2-Flash: 59.7 (#106)

| Benchmark | Gemma 3 4B | MiMo-V2-Flash |
|---|---|---|
| LMArena Text | 1291 | 1411 |
| LMArena Creative Writing | 1271 | 1375 |
| LMArena Multi-Turn | 1255 | 1404 |
| EQ-Bench Creative Writing | 1068 | — |

## FAQ

### Is Gemma 3 4B better than MiMo-V2-Flash?

MiMo-V2-Flash is the stronger model overall, scoring 41.3 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-Flash's lead doesn't matter for your workload.

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

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

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

They score almost the same on coding (35.9 vs 36.1); test both on your own repository before choosing.

### Which has the bigger context window?

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

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

12 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and MiMo-V2-Flash has 21.