# Granite 4.2 8B vs MiMo-V2.6-Pro

> MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 40.5 on the Noometry Index. Granite 4.2 8B costs 5.1× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/granite-4-2-8b-vs-mimo-v2-6-pro
- Last updated: 2026-10-12
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 0 categories and MiMo-V2.6-Pro in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.6-Pro leads 66.8 to 49.6.
- Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 131K.

## Snapshot

| | Granite 4.2 8B | MiMo-V2.6-Pro |
|---|---|---|
| Provider | IBM | Xiaomi |
| Noometry Index | 40.5 | 50.3 |
| Rank | 148 | 49 |
| Context | 131K | 1.05M |
| Input $/M | $0.06 | $0.43 |
| Output $/M | $0.25 | $0.87 |
| Weights | Open | Open |

## Coding

- Granite 4.2 8B: 40.5 (#137)
- MiMo-V2.6-Pro: 55.5 (#23)

| Benchmark | Granite 4.2 8B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Coding | 1380 | 1534 |
| LMArena WebDev | — | 1629 |
| SciCode | — | 60.9% |
| ALE-Bench | — | 1,158 |

## Agentic & Tool Use

- Granite 4.2 8B: —
- MiMo-V2.6-Pro: 37.5 (#35)

| Benchmark | Granite 4.2 8B | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |

## Reasoning

- Granite 4.2 8B: 26.6 (#131)
- MiMo-V2.6-Pro: 43.1 (#50)

| Benchmark | Granite 4.2 8B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1329 | 1512 |
| CritPt | — | 26.6% |

## Math

- Granite 4.2 8B: —
- MiMo-V2.6-Pro: 54.5 (#45)

| Benchmark | Granite 4.2 8B | MiMo-V2.6-Pro |
|---|---|---|
| ProofBench | — | 70% |
| LMArena Math | — | 1494 |

## Knowledge

- Granite 4.2 8B: 38.4 (#145)
- MiMo-V2.6-Pro: 43.5 (#92)

| Benchmark | Granite 4.2 8B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1384 | 1543 |

## Multimodal

- Granite 4.2 8B: —
- MiMo-V2.6-Pro: 40.8 (#43)

| Benchmark | Granite 4.2 8B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |

## Multilingual

- Granite 4.2 8B: 44.5 (#178)
- MiMo-V2.6-Pro: 56.9 (#14)

| Benchmark | Granite 4.2 8B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1302 | 1474 |
| LMArena Chinese | 1366 | 1529 |
| LMArena Russian | 1285 | 1480 |

## Instruction Following

- Granite 4.2 8B: 68.7 (#184)
- MiMo-V2.6-Pro: 78.2 (#12)

| Benchmark | Granite 4.2 8B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1301 | 1493 |

## Long Context

- Granite 4.2 8B: 40.3 (#159)
- MiMo-V2.6-Pro: 46.0 (#27)

| Benchmark | Granite 4.2 8B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1324 | 1501 |

## Writing & Preference

- Granite 4.2 8B: 49.6 (#189)
- MiMo-V2.6-Pro: 66.8 (#33)

| Benchmark | Granite 4.2 8B | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1320 | 1492 |
| LMArena Creative Writing | 1236 | 1468 |
| LMArena Multi-Turn | 1301 | 1464 |

## FAQ

### Is Granite 4.2 8B better than MiMo-V2.6-Pro?

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 40.5 on the Noometry Index. Granite 4.2 8B costs 5.1× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.

### Which is cheaper, Granite 4.2 8B or MiMo-V2.6-Pro?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.

### Is Granite 4.2 8B or MiMo-V2.6-Pro better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 40.5 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.6-Pro does, with 1.05M tokens against 131K.

### How many benchmarks do Granite 4.2 8B and MiMo-V2.6-Pro share?

11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and MiMo-V2.6-Pro has 19.