# Gemma 4 31B IT vs MiMo-V2.5

> Gemma 4 31B IT and MiMo-V2.5 score almost the same on the Noometry Index (43.2 vs 43.0), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gemma-4-31b-it-vs-mimo-v2-5
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Gemma 4 31B IT scores higher in 4 categories and MiMo-V2.5 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 31B IT leads 41.3 to 35.4.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2.5.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 262K.

## Snapshot

| | Gemma 4 31B IT | MiMo-V2.5 |
|---|---|---|
| Provider | Google | Xiaomi |
| Noometry Index | 43.2 | 43.0 |
| Rank | 85 | 89 |
| Context | 262K | 1.05M |
| Input $/M | $0.09 | $0.14 |
| Output $/M | $0.34 | $0.28 |
| Weights | Open | Open |

## Coding

- Gemma 4 31B IT: 41.9 (#98)
- MiMo-V2.5: 43.6 (#75)

| Benchmark | Gemma 4 31B IT | MiMo-V2.5 |
|---|---|---|
| LMArena WebDev | 1364 | 1438 |
| SciCode | 43.4% | 43.1% |
| LMArena Coding | 1459 | 1469 |
| ALE-Bench | 925.5 | 513.95 |
| WeirdML | 52.3% | — |

## Reasoning

- Gemma 4 31B IT: 26.4 (#119)
- MiMo-V2.5: 27.8 (#98)

| Benchmark | Gemma 4 31B IT | MiMo-V2.5 |
|---|---|---|
| CritPt | 1.4% | 3.7% |
| LMArena Hard Prompts | 1448 | 1450 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |

## Math

- Gemma 4 31B IT: 41.3 (#72)
- MiMo-V2.5: 35.4 (#145)

| Benchmark | Gemma 4 31B IT | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1464 | 1436 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| ProofBench | — | 16% |

## Knowledge

- Gemma 4 31B IT: 37.9 (#141)
- MiMo-V2.5: 40.2 (#109)

| Benchmark | Gemma 4 31B IT | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1465 | 1459 |
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |

## Multimodal

- Gemma 4 31B IT: 41.0 (#32)
- MiMo-V2.5: 39.0 (#53)

| Benchmark | Gemma 4 31B IT | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | 1278 | 1245 |
| LMArena Document | 1425 | — |

## Multilingual

- Gemma 4 31B IT: 54.0 (#52)
- MiMo-V2.5: 52.0 (#96)

| Benchmark | Gemma 4 31B IT | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1431 | 1404 |
| LMArena Chinese | 1478 | 1467 |
| LMArena French | 1436 | 1447 |
| LMArena Russian | 1462 | 1395 |
| LMArena Spanish | 1443 | 1412 |
| LMArena German | — | 1421 |
| LMArena Japanese | — | 1304 |
| LMArena Korean | — | 1363 |

## Instruction Following

- Gemma 4 31B IT: 75.6 (#58)
- MiMo-V2.5: 75.7 (#55)

| Benchmark | Gemma 4 31B IT | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1433 | 1433 |

## Long Context

- Gemma 4 31B IT: 44.2 (#67)
- MiMo-V2.5: 44.1 (#69)

| Benchmark | Gemma 4 31B IT | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1446 | 1444 |

## Writing & Preference

- Gemma 4 31B IT: 60.7 (#92)
- MiMo-V2.5: 61.8 (#82)

| Benchmark | Gemma 4 31B IT | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1443 | 1427 |
| LMArena Creative Writing | 1416 | 1392 |
| LMArena Multi-Turn | 1452 | 1445 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |

## FAQ

### Is Gemma 4 31B IT better than MiMo-V2.5?

Gemma 4 31B IT and MiMo-V2.5 score almost the same on the Noometry Index (43.2 vs 43.0), so choose on price, context window or the category you care about most.

### Which is cheaper, Gemma 4 31B IT or MiMo-V2.5?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; MiMo-V2.5 lists at $0.14 and $0.28.

### Is Gemma 4 31B IT or MiMo-V2.5 better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 41.9 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 262K.

### How many benchmarks do Gemma 4 31B IT and MiMo-V2.5 share?

19 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and MiMo-V2.5 has 23.