# MiMo-V2-Pro vs Phi 3 Medium 4k Instruct

> MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-pro-vs-phi-3-medium-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. MiMo-V2-Pro scores higher in 8 categories and Phi 3 Medium 4k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.9 to 34.3.
- Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | MiMo-V2-Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | Xiaomi | Microsoft |
| Noometry Index | 42.4 | 32.4 |
| Rank | 102 | 246 |
| Context | 1.05M | — |
| Input $/M | $0.43 | — |
| Output $/M | $0.87 | — |
| Weights | Proprietary | Open |

## Coding

- MiMo-V2-Pro: 43.4 (#76)
- Phi 3 Medium 4k Instruct: 32.3 (#263)

| Benchmark | MiMo-V2-Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1476 | 1130 |
| LMArena WebDev | 1433 | — |
| ALE-Bench | 785.17 | — |

## Reasoning

- MiMo-V2-Pro: 21.3 (#200)
- Phi 3 Medium 4k Instruct: 20.8 (#214)

| Benchmark | MiMo-V2-Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1127 |
| NYT Connections (extended) | 25.8% | — |
| Thematic Generalization | 45.9% | — |

## Math

- MiMo-V2-Pro: 36.7 (#104)
- Phi 3 Medium 4k Instruct: 30.9 (#202)

| Benchmark | MiMo-V2-Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1447 | 1173 |

## Knowledge

- MiMo-V2-Pro: 40.8 (#106)
- Phi 3 Medium 4k Instruct: 29.6 (#226)

| Benchmark | MiMo-V2-Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1479 | 1108 |

## Multilingual

- MiMo-V2-Pro: 52.9 (#77)
- Phi 3 Medium 4k Instruct: 30.8 (#258)

| Benchmark | MiMo-V2-Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1416 | 1094 |
| LMArena Chinese | 1455 | 1108 |
| LMArena French | 1470 | 1109 |
| LMArena German | 1417 | 1101 |
| LMArena Japanese | 1366 | 1042 |
| LMArena Korean | 1401 | 954 |
| LMArena Russian | 1427 | 1145 |
| LMArena Spanish | 1458 | 1095 |

## Instruction Following

- MiMo-V2-Pro: 76.2 (#46)
- Phi 3 Medium 4k Instruct: 57.8 (#263)

| Benchmark | MiMo-V2-Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1444 | 1114 |

## Long Context

- MiMo-V2-Pro: 41.5 (#133)
- Phi 3 Medium 4k Instruct: 33.9 (#250)

| Benchmark | MiMo-V2-Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1455 | 1120 |
| CL-bench | 15.7% | — |
| CL-bench Life | 6.9% | — |

## Writing & Preference

- MiMo-V2-Pro: 62.9 (#67)
- Phi 3 Medium 4k Instruct: 34.3 (#267)

| Benchmark | MiMo-V2-Pro | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1436 | 1138 |
| LMArena Creative Writing | 1415 | 1106 |
| LMArena Multi-Turn | 1456 | 1088 |

## FAQ

### Is MiMo-V2-Pro better than Phi 3 Medium 4k Instruct?

MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 32.4 on the Noometry Index.

### Is MiMo-V2-Pro or Phi 3 Medium 4k Instruct better for coding?

MiMo-V2-Pro scores higher on coding benchmarks: 43.4 versus 32.3 in the Noometry coding category.

### How many benchmarks do MiMo-V2-Pro and Phi 3 Medium 4k Instruct share?

17 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.