# Mistral Small 3.1 vs Phi-4

> Mistral Small 3.1 and Phi-4 score almost the same on the Noometry Index (31.7 vs 31.2), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/mistral-small-3-1-vs-phi-4
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Mistral Small 3.1 scores higher in 5 categories and Phi-4 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi-4 leads 32.6 to 22.6.
- The biggest single-benchmark swing is GPQA Diamond: 41.9% for Mistral Small 3.1 and 56.1% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.35 / $0.56 for Mistral Small 3.1.

## Snapshot

| | Mistral Small 3.1 | Phi-4 |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 31.7 | 31.2 |
| Rank | 269 | 279 |
| Context | 128K | 128K |
| Input $/M | $0.35 | $0.07 |
| Output $/M | $0.56 | $0.14 |
| Weights | Open | Open |

## Coding

- Mistral Small 3.1: 38.3 (#179)
- Phi-4: 34.4 (#239)

| Benchmark | Mistral Small 3.1 | Phi-4 |
|---|---|---|
| LMArena Coding | 1309 | 1231 |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |

## Agentic & Tool Use

- Mistral Small 3.1: —
- Phi-4: 22.8 (#128)

| Benchmark | Mistral Small 3.1 | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |

## Reasoning

- Mistral Small 3.1: 19.7 (#254)
- Phi-4: 17.7 (#291)

| Benchmark | Mistral Small 3.1 | Phi-4 |
|---|---|---|
| Chess Puzzles | 1% | 1% |
| LMArena Hard Prompts | 1278 | 1220 |
| Epoch Capabilities Index | 127.48 | 130.42 |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| LiveBench | — | 41.6% |

## Math

- Mistral Small 3.1: 14.7 (#301)
- Phi-4: 20.8 (#285)

| Benchmark | Mistral Small 3.1 | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.9% | 13.8% |
| LMArena Math | 1262 | 1246 |
| Omni-MATH | 24.8% | — |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |

## Knowledge

- Mistral Small 3.1: 22.6 (#271)
- Phi-4: 32.6 (#209)

| Benchmark | Mistral Small 3.1 | Phi-4 |
|---|---|---|
| GPQA Diamond | 41.9% | 56.1% |
| LMArena Expert | 1257 | 1203 |
| MMLU-Pro | 61% | — |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| GPQA (HELM) | 39.2% | — |
| MMLU | — | 84.8% |

## Multimodal

- Mistral Small 3.1: 33.2 (#99)
- Phi-4: —

| Benchmark | Mistral Small 3.1 | Phi-4 |
|---|---|---|
| LMArena Vision | 1136 | — |

## Multilingual

- Mistral Small 3.1: 41.2 (#209)
- Phi-4: 37.2 (#237)

| Benchmark | Mistral Small 3.1 | Phi-4 |
|---|---|---|
| LMArena Non-English | 1255 | 1197 |
| LMArena Chinese | 1253 | 1212 |
| LMArena French | 1273 | 1224 |
| LMArena German | 1266 | 1222 |
| LMArena Japanese | 1208 | 1158 |
| LMArena Korean | 1206 | 1151 |
| LMArena Russian | 1263 | 1209 |
| LMArena Spanish | 1283 | 1234 |

## Instruction Following

- Mistral Small 3.1: 63.6 (#230)
- Phi-4: 60.4 (#251)

| Benchmark | Mistral Small 3.1 | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1264 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
| IFEval | 75% | — |

## Long Context

- Mistral Small 3.1: 39.5 (#178)
- Phi-4: 36.9 (#226)

| Benchmark | Mistral Small 3.1 | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1299 | 1217 |

## Writing & Preference

- Mistral Small 3.1: 37.0 (#259)
- Phi-4: 40.5 (#244)

| Benchmark | Mistral Small 3.1 | Phi-4 |
|---|---|---|
| LMArena Text | 1277 | 1217 |
| LMArena Creative Writing | 1253 | 1182 |
| LMArena Multi-Turn | 1270 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| EQ-Bench Creative Writing | 761 | — |
| WildBench | 78.8% | — |
| LiveBench Language | — | 25.6% |

## FAQ

### Is Mistral Small 3.1 better than Phi-4?

Mistral Small 3.1 and Phi-4 score almost the same on the Noometry Index (31.7 vs 31.2), so choose on price, context window or the category you care about most.

### Which is cheaper, Mistral Small 3.1 or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Mistral Small 3.1 lists at $0.35 and $0.56.

### Is Mistral Small 3.1 or Phi-4 better for coding?

Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 34.4 in the Noometry coding category.

### Which has the bigger context window?

Both accept 128K tokens.

### How many benchmarks do Mistral Small 3.1 and Phi-4 share?

21 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and Phi-4 has 37.