# Mistral Large 4 vs phi-3-medium 14B

> Mistral Large 4 is the stronger model overall, scoring 43.1 to 29.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-large-4-vs-phi-3-medium-14b
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Mistral Large 4 leads 36.6 to 9.1.
- phi-3-medium 14B has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Large 4 | phi-3-medium 14B |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 43.1 | 29.7 |
| Rank | 99 | 306 |
| Context | 1.05M | — |
| Input $/M | $0.68 | — |
| Output $/M | $2.09 | — |
| Weights | Proprietary | Open |

## Coding

- Mistral Large 4: 48.6 (#57)
- phi-3-medium 14B: 36.8 (#201)

| Benchmark | Mistral Large 4 | phi-3-medium 14B |
|---|---|---|
| LMArena WebDev | 1541 | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1475 | — |
| BigCodeBench Complete | — | 48.7% |

## Reasoning

- Mistral Large 4: 22.5 (#192)
- phi-3-medium 14B: —

| Benchmark | Mistral Large 4 | phi-3-medium 14B |
|---|---|---|
| NYT Connections (extended) | 27.4% | — |
| LMArena Hard Prompts | 1444 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- Mistral Large 4: 40.4 (#91)
- phi-3-medium 14B: 27.3 (#250)

| Benchmark | Mistral Large 4 | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1488 | — |
| MATH Level 5 | — | 17.6% |

## Knowledge

- Mistral Large 4: 36.6 (#166)
- phi-3-medium 14B: 9.1 (#306)

| Benchmark | Mistral Large 4 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| SimpleQA Verified | 20% | — |
| LMArena Expert | 1447 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multilingual

- Mistral Large 4: 52.6 (#82)
- phi-3-medium 14B: —

| Benchmark | Mistral Large 4 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1415 | — |
| LMArena Chinese | 1491 | — |
| LMArena Russian | 1414 | — |

## Instruction Following

- Mistral Large 4: 75.0 (#76)
- phi-3-medium 14B: —

| Benchmark | Mistral Large 4 | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1424 | — |

## Long Context

- Mistral Large 4: 43.6 (#89)
- phi-3-medium 14B: —

| Benchmark | Mistral Large 4 | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1429 | — |

## Writing & Preference

- Mistral Large 4: 60.4 (#97)
- phi-3-medium 14B: —

| Benchmark | Mistral Large 4 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1427 | — |
| LMArena Creative Writing | 1361 | — |
| LMArena Multi-Turn | 1424 | — |

## FAQ

### Is Mistral Large 4 better than phi-3-medium 14B?

Mistral Large 4 is the stronger model overall, scoring 43.1 to 29.7 on the Noometry Index.

### Is Mistral Large 4 or phi-3-medium 14B better for coding?

Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 36.8 in the Noometry coding category.

### How many benchmarks do Mistral Large 4 and phi-3-medium 14B share?

0 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and phi-3-medium 14B has 13.