# Mistral Small vs Phi 3 Mini 4k Instruct

> Mistral Small is the stronger model overall, scoring 33.4 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-small-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Mistral Small scores higher in 7 categories and Phi 3 Mini 4k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.5 to 27.6.
- The biggest single-benchmark swing is LiveBench Instruction Following: 63.7% for Mistral Small and 39.1% for Phi 3 Mini 4k Instruct.

## Snapshot

| | Mistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 33.4 | 27.9 |
| Rank | 243 | 328 |
| Context | 262K | — |
| Input $/M | $0.15 | — |
| Output $/M | $0.60 | — |
| Weights | Open | Open |

## Coding

- Mistral Small: 34.0 (#247)
- Phi 3 Mini 4k Instruct: 26.6 (#323)

| Benchmark | Mistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 36.2% | 15.5% |
| LMArena Coding | 1362 | 1093 |
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Agentic & Tool Use

- Mistral Small: 28.1 (#93)
- Phi 3 Mini 4k Instruct: —

| Benchmark | Mistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |

## Reasoning

- Mistral Small: 19.8 (#250)
- Phi 3 Mini 4k Instruct: 14.1 (#328)

| Benchmark | Mistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Reasoning | 44.8% | 26.8% |
| LMArena Hard Prompts | 1335 | 1072 |
| LiveBench Data Analysis | 53.7% | 34.7% |
| LiveBench | 44% | 22.4% |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| DTBench | 70.9% | — |
| LMCA | 20.6% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| WinoGrande | — | 70.8% |

## Math

- Mistral Small: 16.4 (#293)
- Phi 3 Mini 4k Instruct: 26.6 (#257)

| Benchmark | Mistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 39.9% | 15.7% |
| LMArena Math | 1341 | 1111 |
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| MATH Level 5 | 46.8% | — |

## Knowledge

- Mistral Small: 31.0 (#222)
- Phi 3 Mini 4k Instruct: 28.5 (#246)

| Benchmark | Mistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1291 | 1045 |
| MMLU | 68.7% | 68.8% |
| GPQA Diamond | 47.5% | — |
| Vectara Hallucination Rate | 5.1% | — |
| ARC (AI2) Challenge | — | 84.9% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multimodal

- Mistral Small: 33.5 (#96)
- Phi 3 Mini 4k Instruct: —

| Benchmark | Mistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1142 | — |

## Multilingual

- Mistral Small: 45.5 (#169)
- Phi 3 Mini 4k Instruct: 26.3 (#280)

| Benchmark | Mistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1315 | 1021 |
| LMArena Chinese | 1340 | 1021 |
| LMArena French | 1337 | 1076 |
| LMArena German | 1340 | 1044 |
| LMArena Japanese | 1275 | 935 |
| LMArena Korean | 1259 | 905 |
| LMArena Russian | 1324 | 1022 |
| LMArena Spanish | 1346 | 1085 |

## Instruction Following

- Mistral Small: 66.4 (#209)
- Phi 3 Mini 4k Instruct: 47.7 (#303)

| Benchmark | Mistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 63.7% | 39.1% |
| LMArena Instruction Following | 1310 | 1053 |

## Long Context

- Mistral Small: 40.4 (#156)
- Phi 3 Mini 4k Instruct: 31.7 (#276)

| Benchmark | Mistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1327 | 1044 |

## Writing & Preference

- Mistral Small: 52.5 (#171)
- Phi 3 Mini 4k Instruct: 27.6 (#300)

| Benchmark | Mistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1338 | 1073 |
| LMArena Creative Writing | 1305 | 1037 |
| LMArena Multi-Turn | 1344 | 1018 |
| LiveBench Language | 30.5% | 9.2% |

## FAQ

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

Mistral Small is the stronger model overall, scoring 33.4 to 27.9 on the Noometry Index.

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

Mistral Small scores higher on coding benchmarks: 34.0 versus 26.6 in the Noometry coding category.

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

25 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.