# Mistral Small 3 vs Phi 3 Mini 4k Instruct

> Mistral Small 3 is the stronger model overall, scoring 31.2 to 27.9 on the Noometry Index.

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

## Summary

- They share 17 benchmarks with published results for both. Mistral Small 3 scores higher in 6 categories and Phi 3 Mini 4k Instruct in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Mistral Small 3 leads 63.7 to 47.7.

## Snapshot

| | Mistral Small 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 31.2 | 27.9 |
| Rank | 278 | 328 |
| Context | 33K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.08 | — |
| Weights | Open | Open |

## Coding

- Mistral Small 3: 36.5 (#207)
- Phi 3 Mini 4k Instruct: 26.6 (#323)

| Benchmark | Mistral Small 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1246 | 1093 |
| BigCodeBench Instruct | 45.3% | — |
| LiveBench Coding | — | 15.5% |
| BigCodeBench Complete | 50.4% | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Reasoning

- Mistral Small 3: 18.9 (#273)
- Phi 3 Mini 4k Instruct: 14.1 (#328)

| Benchmark | Mistral Small 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1233 | 1072 |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 127.07 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |

## Math

- Mistral Small 3: 16.3 (#295)
- Phi 3 Mini 4k Instruct: 26.6 (#257)

| Benchmark | Mistral Small 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1240 | 1111 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| LiveBench Math | — | 15.7% |

## Knowledge

- Mistral Small 3: 25.1 (#263)
- Phi 3 Mini 4k Instruct: 28.5 (#246)

| Benchmark | Mistral Small 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1202 | 1045 |
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multilingual

- Mistral Small 3: 37.3 (#236)
- Phi 3 Mini 4k Instruct: 26.3 (#280)

| Benchmark | Mistral Small 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1198 | 1021 |
| LMArena Chinese | 1204 | 1021 |
| LMArena French | 1203 | 1076 |
| LMArena German | 1211 | 1044 |
| LMArena Japanese | 1111 | 935 |
| LMArena Korean | 1188 | 905 |
| LMArena Russian | 1216 | 1022 |
| LMArena Spanish | — | 1085 |

## Instruction Following

- Mistral Small 3: 63.7 (#229)
- Phi 3 Mini 4k Instruct: 47.7 (#303)

| Benchmark | Mistral Small 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1214 | 1053 |
| LiveBench Instruction Following | — | 39.1% |

## Long Context

- Mistral Small 3: 37.8 (#211)
- Phi 3 Mini 4k Instruct: 31.7 (#276)

| Benchmark | Mistral Small 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1246 | 1044 |

## Writing & Preference

- Mistral Small 3: 32.2 (#280)
- Phi 3 Mini 4k Instruct: 27.6 (#300)

| Benchmark | Mistral Small 3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1234 | 1073 |
| LMArena Creative Writing | 1195 | 1037 |
| LMArena Multi-Turn | 1217 | 1018 |
| EQ-Bench Creative Writing | 707 | — |
| LiveBench Language | — | 9.2% |

## FAQ

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

Mistral Small 3 is the stronger model overall, scoring 31.2 to 27.9 on the Noometry Index.

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

Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 26.6 in the Noometry coding category.

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

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