# Granite 4.2 3b vs MiMo-V2.5

> MiMo-V2.5 is the stronger model overall, scoring 43.4 to 39.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-3b-vs-mimo-v2-5
- Last updated: 2026-10-11
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 3b scores higher in 0 categories and MiMo-V2.5 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.6 to 47.2.

## Snapshot

| | Granite 4.2 3b | MiMo-V2.5 |
|---|---|---|
| Provider | IBM | Xiaomi |
| Noometry Index | 39.4 | 43.4 |
| Rank | 169 | 93 |
| Context | — | 1.05M |
| Input $/M | — | $0.14 |
| Output $/M | — | $0.28 |
| Weights | Open | Open |

## Coding

- Granite 4.2 3b: 40.0 (#151)
- MiMo-V2.5: 43.9 (#81)

| Benchmark | Granite 4.2 3b | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1361 | 1469 |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| ALE-Bench | — | 513.95 |

## Reasoning

- Granite 4.2 3b: 26.0 (#138)
- MiMo-V2.5: 28.6 (#101)

| Benchmark | Granite 4.2 3b | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1306 | 1450 |
| CritPt | — | 3.7% |

## Math

- Granite 4.2 3b: —
- MiMo-V2.5: 36.8 (#163)

| Benchmark | Granite 4.2 3b | MiMo-V2.5 |
|---|---|---|
| ProofBench | — | 16% |
| LMArena Math | — | 1436 |

## Knowledge

- Granite 4.2 3b: 36.3 (#171)
- MiMo-V2.5: 40.8 (#115)

| Benchmark | Granite 4.2 3b | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1315 | 1460 |

## Multimodal

- Granite 4.2 3b: —
- MiMo-V2.5: 39.8 (#54)

| Benchmark | Granite 4.2 3b | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1247 |

## Multilingual

- Granite 4.2 3b: 42.1 (#198)
- MiMo-V2.5: 51.9 (#99)

| Benchmark | Granite 4.2 3b | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1268 | 1404 |
| LMArena Chinese | 1269 | 1468 |
| LMArena Russian | 1249 | 1395 |
| LMArena French | — | 1447 |
| LMArena German | — | 1421 |
| LMArena Japanese | — | 1306 |
| LMArena Korean | — | 1363 |
| LMArena Spanish | — | 1416 |

## Instruction Following

- Granite 4.2 3b: 67.1 (#200)
- MiMo-V2.5: 75.5 (#60)

| Benchmark | Granite 4.2 3b | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1273 | 1434 |

## Long Context

- Granite 4.2 3b: 39.2 (#185)
- MiMo-V2.5: 44.2 (#73)

| Benchmark | Granite 4.2 3b | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1291 | 1445 |

## Writing & Preference

- Granite 4.2 3b: 47.2 (#212)
- MiMo-V2.5: 61.6 (#86)

| Benchmark | Granite 4.2 3b | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1293 | 1428 |
| LMArena Creative Writing | 1205 | 1393 |
| LMArena Multi-Turn | 1290 | 1445 |

## FAQ

### Is Granite 4.2 3b better than MiMo-V2.5?

MiMo-V2.5 is the stronger model overall, scoring 43.4 to 39.4 on the Noometry Index.

### Is Granite 4.2 3b or MiMo-V2.5 better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 40.0 in the Noometry coding category.

### How many benchmarks do Granite 4.2 3b and MiMo-V2.5 share?

11 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and MiMo-V2.5 has 23.