# Granite 4.0 H Small vs MiMo-V2.5-Pro

> MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ibm-granite-h-small-vs-mimo-v2-5-pro
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Granite 4.0 H Small scores higher in 0 categories and MiMo-V2.5-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.5 to 44.0.

## Snapshot

| | Granite 4.0 H Small | MiMo-V2.5-Pro |
|---|---|---|
| Provider | IBM | Xiaomi |
| Noometry Index | 35.9 | 44.8 |
| Rank | 213 | 70 |
| Context | — | 1.05M |
| Input $/M | — | $0.43 |
| Output $/M | — | $0.87 |
| Weights | Open | Open |

## Coding

- Granite 4.0 H Small: 35.8 (#207)
- MiMo-V2.5-Pro: 47.0 (#58)

| Benchmark | Granite 4.0 H Small | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1247 | 1502 |
| LMArena WebDev | — | 1477 |
| SciCode | — | 50.2% |
| ALE-Bench | — | 899.8 |

## Reasoning

- Granite 4.0 H Small: 23.4 (#164)
- MiMo-V2.5-Pro: 25.9 (#124)

| Benchmark | Granite 4.0 H Small | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1487 |
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| DTBench | — | 84.5% |
| LMCA | — | 29.5% |

## Math

- Granite 4.0 H Small: 29.3 (#219)
- MiMo-V2.5-Pro: 38.6 (#84)

| Benchmark | Granite 4.0 H Small | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1251 | 1480 |
| ProofBench | — | 22% |
| Omni-MATH | 29.6% | — |

## Knowledge

- Granite 4.0 H Small: 31.5 (#210)
- MiMo-V2.5-Pro: 41.5 (#100)

| Benchmark | Granite 4.0 H Small | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1244 | 1501 |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |

## Multilingual

- Granite 4.0 H Small: 38.7 (#223)
- MiMo-V2.5-Pro: 55.3 (#33)

| Benchmark | Granite 4.0 H Small | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1216 | 1449 |
| LMArena Chinese | 1250 | 1507 |
| LMArena Russian | 1198 | 1450 |
| LMArena Spanish | 1258 | 1470 |
| LMArena French | — | 1489 |
| LMArena German | — | 1455 |
| LMArena Japanese | — | 1418 |
| LMArena Korean | — | 1436 |

## Instruction Following

- Granite 4.0 H Small: 68.9 (#178)
- MiMo-V2.5-Pro: 77.6 (#21)

| Benchmark | Granite 4.0 H Small | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1221 | 1477 |
| IFEval | 89% | — |

## Long Context

- Granite 4.0 H Small: 37.6 (#209)
- MiMo-V2.5-Pro: 45.4 (#38)

| Benchmark | Granite 4.0 H Small | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1240 | 1482 |

## Writing & Preference

- Granite 4.0 H Small: 44.0 (#222)
- MiMo-V2.5-Pro: 65.5 (#47)

| Benchmark | Granite 4.0 H Small | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1241 | 1465 |
| LMArena Creative Writing | 1210 | 1440 |
| LMArena Multi-Turn | 1243 | 1477 |
| EQ-Bench Creative Writing | — | 1493 |
| WildBench | 73.9% | — |
| EQ-Bench 4 | — | 1208 |

## FAQ

### Is Granite 4.0 H Small better than MiMo-V2.5-Pro?

MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 35.9 on the Noometry Index.

### Is Granite 4.0 H Small or MiMo-V2.5-Pro better for coding?

MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 35.8 in the Noometry coding category.

### How many benchmarks do Granite 4.0 H Small and MiMo-V2.5-Pro share?

13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and MiMo-V2.5-Pro has 27.