# MiMo-V2.6-Pro vs Phi 3 Small 8k Instruct

> MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-6-pro-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.6-Pro leads 66.9 to 31.3.

## Snapshot

| | MiMo-V2.6-Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | Xiaomi | Microsoft |
| Noometry Index | 46.7 | 28.8 |
| Rank | 55 | 310 |
| Context | 1.05M | — |
| Input $/M | $0.43 | — |
| Output $/M | $0.87 | — |
| Weights | Open | Open |

## Coding

- MiMo-V2.6-Pro: 53.2 (#27)
- Phi 3 Small 8k Instruct: 27.4 (#313)

| Benchmark | MiMo-V2.6-Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1538 | 1102 |
| LMArena WebDev | 1618 | — |
| LiveBench Coding | — | 20.3% |

## Reasoning

- MiMo-V2.6-Pro: 30.4 (#76)
- Phi 3 Small 8k Instruct: 14.2 (#319)

| Benchmark | MiMo-V2.6-Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1511 | 1100 |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |

## Math

- MiMo-V2.6-Pro: 37.9 (#91)
- Phi 3 Small 8k Instruct: 25.4 (#247)

| Benchmark | MiMo-V2.6-Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1497 | 1151 |
| LiveBench Math | — | 17.6% |

## Knowledge

- MiMo-V2.6-Pro: 43.0 (#85)
- Phi 3 Small 8k Instruct: 28.5 (#237)

| Benchmark | MiMo-V2.6-Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1548 | 1067 |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multimodal

- MiMo-V2.6-Pro: 40.2 (#40)
- Phi 3 Small 8k Instruct: —

| Benchmark | MiMo-V2.6-Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 1265 | — |

## Multilingual

- MiMo-V2.6-Pro: 57.0 (#15)
- Phi 3 Small 8k Instruct: 28.6 (#267)

| Benchmark | MiMo-V2.6-Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1474 | 1058 |
| LMArena Chinese | 1532 | 1061 |
| LMArena Russian | 1481 | 1111 |
| LMArena French | — | 1134 |
| LMArena German | — | 1080 |
| LMArena Japanese | — | 966 |
| LMArena Korean | — | 894 |
| LMArena Spanish | — | 1111 |

## Instruction Following

- MiMo-V2.6-Pro: 78.2 (#10)
- Phi 3 Small 8k Instruct: 52.2 (#287)

| Benchmark | MiMo-V2.6-Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1490 | 1087 |
| LiveBench Instruction Following | — | 47.2% |

## Long Context

- MiMo-V2.6-Pro: 46.0 (#26)
- Phi 3 Small 8k Instruct: 33.0 (#262)

| Benchmark | MiMo-V2.6-Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1500 | 1088 |

## Writing & Preference

- MiMo-V2.6-Pro: 66.9 (#32)
- Phi 3 Small 8k Instruct: 31.3 (#279)

| Benchmark | MiMo-V2.6-Pro | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1491 | 1110 |
| LMArena Creative Writing | 1465 | 1083 |
| LMArena Multi-Turn | 1463 | 1068 |
| LiveBench Language | — | 12.9% |

## FAQ

### Is MiMo-V2.6-Pro better than Phi 3 Small 8k Instruct?

MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 28.8 on the Noometry Index.

### Is MiMo-V2.6-Pro or Phi 3 Small 8k Instruct better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 53.2 versus 27.4 in the Noometry coding category.

### How many benchmarks do MiMo-V2.6-Pro and Phi 3 Small 8k Instruct share?

12 benchmarks have published results for both models. MiMo-V2.6-Pro has 14 scored results on Noometry and Phi 3 Small 8k Instruct has 32.