# Granite 3.0 8b Instruct vs MiMo-V2.5

> MiMo-V2.5 is the stronger model overall, scoring 43.0 to 31.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-0-8b-instruct-vs-mimo-v2-5
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Granite 3.0 8b Instruct scores higher in 0 categories and MiMo-V2.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.8 to 31.2.

## Snapshot

| | Granite 3.0 8b Instruct | MiMo-V2.5 |
|---|---|---|
| Provider | IBM | Xiaomi |
| Noometry Index | 31.1 | 43.0 |
| Rank | 266 | 89 |
| Context | — | 1.05M |
| Input $/M | — | $0.14 |
| Output $/M | — | $0.28 |
| Weights | Open | Open |

## Coding

- Granite 3.0 8b Instruct: 29.1 (#297)
- MiMo-V2.5: 43.6 (#75)

| Benchmark | Granite 3.0 8b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1113 | 1469 |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| BigCodeBench Instruct | 29.3% | — |
| BigCodeBench Complete | 35.4% | — |
| ALE-Bench | — | 513.95 |

## Reasoning

- Granite 3.0 8b Instruct: 20.0 (#227)
- MiMo-V2.5: 27.8 (#98)

| Benchmark | Granite 3.0 8b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1092 | 1450 |
| CritPt | — | 3.7% |

## Math

- Granite 3.0 8b Instruct: 30.3 (#211)
- MiMo-V2.5: 35.4 (#145)

| Benchmark | Granite 3.0 8b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1143 | 1436 |
| ProofBench | — | 16% |

## Knowledge

- Granite 3.0 8b Instruct: 29.1 (#233)
- MiMo-V2.5: 40.2 (#109)

| Benchmark | Granite 3.0 8b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1087 | 1459 |

## Multimodal

- Granite 3.0 8b Instruct: —
- MiMo-V2.5: 39.0 (#53)

| Benchmark | Granite 3.0 8b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1245 |

## Multilingual

- Granite 3.0 8b Instruct: 27.4 (#271)
- MiMo-V2.5: 52.0 (#96)

| Benchmark | Granite 3.0 8b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1037 | 1404 |
| LMArena Chinese | 1063 | 1467 |
| LMArena Russian | 1060 | 1395 |
| LMArena French | — | 1447 |
| LMArena German | — | 1421 |
| LMArena Japanese | — | 1304 |
| LMArena Korean | — | 1363 |
| LMArena Spanish | — | 1412 |

## Instruction Following

- Granite 3.0 8b Instruct: 56.2 (#271)
- MiMo-V2.5: 75.7 (#55)

| Benchmark | Granite 3.0 8b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1088 | 1433 |

## Long Context

- Granite 3.0 8b Instruct: 34.0 (#247)
- MiMo-V2.5: 44.1 (#69)

| Benchmark | Granite 3.0 8b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1122 | 1444 |

## Writing & Preference

- Granite 3.0 8b Instruct: 31.2 (#280)
- MiMo-V2.5: 61.8 (#82)

| Benchmark | Granite 3.0 8b Instruct | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1096 | 1427 |
| LMArena Creative Writing | 1071 | 1392 |
| LMArena Multi-Turn | 1063 | 1445 |

## FAQ

### Is Granite 3.0 8b Instruct better than MiMo-V2.5?

MiMo-V2.5 is the stronger model overall, scoring 43.0 to 31.1 on the Noometry Index.

### Is Granite 3.0 8b Instruct or MiMo-V2.5 better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 29.1 in the Noometry coding category.

### How many benchmarks do Granite 3.0 8b Instruct and MiMo-V2.5 share?

12 benchmarks have published results for both models. Granite 3.0 8b Instruct has 14 scored results on Noometry and MiMo-V2.5 has 23.