# Mistral Medium vs Phi 3 Mini 128k Instruct

> Mistral Medium is the stronger model overall, scoring 36.0 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-medium-vs-phi-3-mini-128k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Mistral Medium scores higher in 6 categories and Phi 3 Mini 128k Instruct in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.2 to 27.3.

## Snapshot

| | Mistral Medium | Phi 3 Mini 128k Instruct |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 36.0 | 29.1 |
| Rank | 211 | 303 |
| Context | 262K | — |
| Input $/M | $1.50 | — |
| Output $/M | $7.50 | — |
| Weights | Open | Open |

## Coding

- Mistral Medium: 33.8 (#241)
- Phi 3 Mini 128k Instruct: 28.3 (#307)

| Benchmark | Mistral Medium | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1434 | 1040 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 763.98 | — |

## Agentic & Tool Use

- Mistral Medium: 28.1 (#84)
- Phi 3 Mini 128k Instruct: —

| Benchmark | Mistral Medium | Phi 3 Mini 128k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |

## Reasoning

- Mistral Medium: 23.3 (#165)
- Phi 3 Mini 128k Instruct: 18.7 (#254)

| Benchmark | Mistral Medium | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1028 |
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |

## Math

- Mistral Medium: 27.2 (#238)
- Phi 3 Mini 128k Instruct: 29.2 (#220)

| Benchmark | Mistral Medium | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1409 | 1089 |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |

## Knowledge

- Mistral Medium: 24.9 (#260)
- Phi 3 Mini 128k Instruct: 26.3 (#251)

| Benchmark | Mistral Medium | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1408 | 984 |
| GPQA Diamond | 59.5% | — |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |

## Multimodal

- Mistral Medium: 34.6 (#82)
- Phi 3 Mini 128k Instruct: —

| Benchmark | Mistral Medium | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Vision | 1172 | — |

## Multilingual

- Mistral Medium: 52.3 (#86)
- Phi 3 Mini 128k Instruct: 25.4 (#280)

| Benchmark | Mistral Medium | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1408 | 1000 |
| LMArena Chinese | 1448 | 1016 |
| LMArena French | 1460 | 1038 |
| LMArena German | 1433 | 1006 |
| LMArena Japanese | 1378 | 899 |
| LMArena Korean | 1382 | 856 |
| LMArena Russian | 1411 | 1004 |
| LMArena Spanish | 1433 | 1058 |

## Instruction Following

- Mistral Medium: 73.9 (#111)
- Phi 3 Mini 128k Instruct: 52.1 (#289)

| Benchmark | Mistral Medium | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1398 | 1023 |

## Long Context

- Mistral Medium: 42.9 (#108)
- Phi 3 Mini 128k Instruct: 30.3 (#284)

| Benchmark | Mistral Medium | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1406 | 996 |

## Writing & Preference

- Mistral Medium: 60.2 (#97)
- Phi 3 Mini 128k Instruct: 27.3 (#296)

| Benchmark | Mistral Medium | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1424 | 1050 |
| LMArena Creative Writing | 1391 | 1024 |
| LMArena Multi-Turn | 1418 | 989 |
| Short-Story Creative Writing | 77.3% | — |

## FAQ

### Is Mistral Medium better than Phi 3 Mini 128k Instruct?

Mistral Medium is the stronger model overall, scoring 36.0 to 29.1 on the Noometry Index.

### Is Mistral Medium or Phi 3 Mini 128k Instruct better for coding?

Mistral Medium scores higher on coding benchmarks: 33.8 versus 28.3 in the Noometry coding category.

### How many benchmarks do Mistral Medium and Phi 3 Mini 128k Instruct share?

17 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.