# MiMo-V2.6-Pro vs Mistral Small

> MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 33.4 on the Noometry Index. Mistral Small costs 2.1× 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/mimo-v2-6-pro-vs-mistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 10 categories and Mistral Small in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Pro leads 54.5 to 16.4.
- The biggest single-benchmark swing is SciCode: 60.9% for MiMo-V2.6-Pro and 26.5% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 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 262K.

## Snapshot

| | MiMo-V2.6-Pro | Mistral Small |
|---|---|---|
| Provider | Xiaomi | Mistral AI |
| Noometry Index | 50.3 | 33.4 |
| Rank | 49 | 243 |
| Context | 1.05M | 262K |
| Input $/M | $0.43 | $0.15 |
| Output $/M | $0.87 | $0.60 |
| Weights | Open | Open |

## Coding

- MiMo-V2.6-Pro: 55.5 (#23)
- Mistral Small: 34.0 (#247)

| Benchmark | MiMo-V2.6-Pro | Mistral Small |
|---|---|---|
| SciCode | 60.9% | 26.5% |
| LMArena Coding | 1534 | 1362 |
| ALE-Bench | 1,158 | 497.62 |
| LMArena WebDev | 1629 | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |

## Agentic & Tool Use

- MiMo-V2.6-Pro: 37.5 (#35)
- Mistral Small: 28.1 (#93)

| Benchmark | MiMo-V2.6-Pro | Mistral Small |
|---|---|---|
| APEX-Agents | 59.5% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- MiMo-V2.6-Pro: 43.1 (#50)
- Mistral Small: 19.8 (#250)

| Benchmark | MiMo-V2.6-Pro | Mistral Small |
|---|---|---|
| CritPt | 26.6% | 0% |
| LMArena Hard Prompts | 1512 | 1335 |
| Kagi LLM Benchmark | — | 37.8% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |

## Math

- MiMo-V2.6-Pro: 54.5 (#45)
- Mistral Small: 16.4 (#293)

| Benchmark | MiMo-V2.6-Pro | Mistral Small |
|---|---|---|
| LMArena Math | 1494 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| ProofBench | 70% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |

## Knowledge

- MiMo-V2.6-Pro: 43.5 (#92)
- Mistral Small: 31.0 (#222)

| Benchmark | MiMo-V2.6-Pro | Mistral Small |
|---|---|---|
| LMArena Expert | 1543 | 1291 |
| GPQA Diamond | — | 47.5% |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |

## Multimodal

- MiMo-V2.6-Pro: 40.8 (#43)
- Mistral Small: 33.5 (#96)

| Benchmark | MiMo-V2.6-Pro | Mistral Small |
|---|---|---|
| LMArena Vision | 1264 | 1142 |

## Multilingual

- MiMo-V2.6-Pro: 56.9 (#14)
- Mistral Small: 45.5 (#169)

| Benchmark | MiMo-V2.6-Pro | Mistral Small |
|---|---|---|
| LMArena Non-English | 1474 | 1315 |
| LMArena Chinese | 1529 | 1340 |
| LMArena Russian | 1480 | 1324 |
| LMArena French | — | 1337 |
| LMArena German | — | 1340 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1259 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- MiMo-V2.6-Pro: 78.2 (#12)
- Mistral Small: 66.4 (#209)

| Benchmark | MiMo-V2.6-Pro | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1493 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- MiMo-V2.6-Pro: 46.0 (#27)
- Mistral Small: 40.4 (#156)

| Benchmark | MiMo-V2.6-Pro | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1501 | 1327 |

## Writing & Preference

- MiMo-V2.6-Pro: 66.8 (#33)
- Mistral Small: 52.5 (#171)

| Benchmark | MiMo-V2.6-Pro | Mistral Small |
|---|---|---|
| LMArena Text | 1492 | 1338 |
| LMArena Creative Writing | 1468 | 1305 |
| LMArena Multi-Turn | 1464 | 1344 |
| LiveBench Language | — | 30.5% |

## FAQ

### Is MiMo-V2.6-Pro better than Mistral Small?

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 33.4 on the Noometry Index. Mistral Small costs 2.1× 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, MiMo-V2.6-Pro or Mistral Small?

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.

### Is MiMo-V2.6-Pro or Mistral Small better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 34.0 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.6-Pro does, with 1.05M tokens against 262K.

### How many benchmarks do MiMo-V2.6-Pro and Mistral Small share?

16 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Mistral Small has 39.