# Mistral Large 3 vs Phi 3 Mini 4k Instruct

> Mistral Large 3 is the stronger model overall, scoring 39.1 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-large-3-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Mistral Large 3 scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.0 to 27.6.

## Snapshot

| | Mistral Large 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 39.1 | 27.9 |
| Rank | 176 | 328 |
| Context | 262K | — |
| Input $/M | $0.25 | — |
| Output $/M | $0.75 | — |
| Weights | Open | Open |

## Coding

- Mistral Large 3: 34.4 (#237)
- Phi 3 Mini 4k Instruct: 26.6 (#323)

| Benchmark | Mistral Large 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1448 | 1093 |
| LMArena WebDev | 1230 | — |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Reasoning

- Mistral Large 3: 15.2 (#319)
- Phi 3 Mini 4k Instruct: 14.1 (#328)

| Benchmark | Mistral Large 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1072 |
| Kagi LLM Benchmark | 50.9% | — |
| NYT Connections (extended) | 7.5% | — |
| Chess Puzzles | — | 0% |
| Thematic Generalization | 23% | — |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |

## Math

- Mistral Large 3: 38.7 (#129)
- Phi 3 Mini 4k Instruct: 26.6 (#257)

| Benchmark | Mistral Large 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1414 | 1111 |
| LiveBench Math | — | 15.7% |

## Knowledge

- Mistral Large 3: 36.0 (#177)
- Phi 3 Mini 4k Instruct: 28.5 (#246)

| Benchmark | Mistral Large 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1421 | 1045 |
| Vectara Hallucination Rate | 14.5% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multimodal

- Mistral Large 3: 38.2 (#66)
- Phi 3 Mini 4k Instruct: —

| Benchmark | Mistral Large 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1221 | — |

## Multilingual

- Mistral Large 3: 52.5 (#84)
- Phi 3 Mini 4k Instruct: 26.3 (#280)

| Benchmark | Mistral Large 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1413 | 1021 |
| LMArena Chinese | 1447 | 1021 |
| LMArena French | 1455 | 1076 |
| LMArena German | 1437 | 1044 |
| LMArena Japanese | 1394 | 935 |
| LMArena Korean | 1384 | 905 |
| LMArena Russian | 1411 | 1022 |
| LMArena Spanish | 1440 | 1085 |

## Instruction Following

- Mistral Large 3: 74.0 (#108)
- Phi 3 Mini 4k Instruct: 47.7 (#303)

| Benchmark | Mistral Large 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1403 | 1053 |
| LiveBench Instruction Following | — | 39.1% |

## Long Context

- Mistral Large 3: 43.1 (#105)
- Phi 3 Mini 4k Instruct: 31.7 (#276)

| Benchmark | Mistral Large 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1413 | 1044 |

## Writing & Preference

- Mistral Large 3: 60.0 (#101)
- Phi 3 Mini 4k Instruct: 27.6 (#300)

| Benchmark | Mistral Large 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1428 | 1073 |
| LMArena Creative Writing | 1386 | 1037 |
| LMArena Multi-Turn | 1429 | 1018 |
| EQ-Bench Creative Writing | 1412 | — |
| LiveBench Language | — | 9.2% |

## FAQ

### Is Mistral Large 3 better than Phi 3 Mini 4k Instruct?

Mistral Large 3 is the stronger model overall, scoring 39.1 to 27.9 on the Noometry Index.

### Is Mistral Large 3 or Phi 3 Mini 4k Instruct better for coding?

Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 26.6 in the Noometry coding category.

### How many benchmarks do Mistral Large 3 and Phi 3 Mini 4k Instruct share?

17 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.