# Mistral Small vs Phi-4

> Mistral Small is the stronger model overall, scoring 33.1 to 30.9 on the Noometry Index. Phi-4 costs 3.0× less per token, which makes it the better buy when Mistral Small's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-small-vs-phi-4
- Last updated: 2026-10-10
- Shared benchmarks: 32

## Summary

- They share 32 benchmarks with published results for both. Mistral Small scores higher in 6 categories and Phi-4 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.6 to 40.7.
- The biggest single-benchmark swing is MATH Level 5: 46.8% for Mistral Small and 64.9% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- Mistral Small accepts more context: 256K tokens versus 128K.

## Snapshot

| | Mistral Small | Phi-4 |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 33.1 | 30.9 |
| Rank | 238 | 269 |
| Context | 256K | 128K |
| Input $/M | $0.15 | $0.07 |
| Output $/M | $0.60 | $0.14 |
| Weights | Open | Open |

## Coding

- Mistral Small: 33.5 (#242)
- Phi-4: 33.8 (#237)

| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| BigCodeBench Instruct | 36.1% | 45.5% |
| LiveBench Coding | 36.2% | 30.7% |
| LMArena Coding | 1363 | 1231 |
| BigCodeBench Complete | 46.6% | 55.4% |
| SciCode | 26.5% | — |
| ALE-Bench | 497.62 | — |

## Agentic & Tool Use

- Mistral Small: 27.9 (#87)
- Phi-4: 22.6 (#120)

| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | 28.8% |
| BALROG | — | 11.6% |

## Reasoning

- Mistral Small: 19.3 (#238)
- Phi-4: 17.0 (#287)

| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| LiveBench Reasoning | 44.8% | 47.8% |
| LMArena Hard Prompts | 1336 | 1220 |
| LiveBench Data Analysis | 53.7% | 45.2% |
| LiveBench | 44% | 41.6% |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 1% |
| DTBench | 70.9% | — |
| LMCA | 20.6% | — |
| Epoch Capabilities Index | — | 130.43 |

## Math

- Mistral Small: 15.4 (#287)
- Phi-4: 19.6 (#279)

| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 13.8% |
| LiveBench Math | 39.9% | 42% |
| LMArena Math | 1341 | 1246 |
| MATH Level 5 | 46.8% | 64.9% |

## Knowledge

- Mistral Small: 30.9 (#214)
- Phi-4: 32.5 (#204)

| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| GPQA Diamond | 47.5% | 56.1% |
| Vectara Hallucination Rate | 5.1% | 3.7% |
| LMArena Expert | 1293 | 1203 |
| MMLU | 68.7% | 84.8% |
| Confabulations | — | 29.4% |

## Multimodal

- Mistral Small: 32.9 (#91)
- Phi-4: —

| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| LMArena Vision | 1142 | — |

## Multilingual

- Mistral Small: 45.7 (#164)
- Phi-4: 37.4 (#232)

| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| LMArena Non-English | 1315 | 1197 |
| LMArena Chinese | 1342 | 1211 |
| LMArena French | 1337 | 1223 |
| LMArena German | 1341 | 1222 |
| LMArena Japanese | 1275 | 1158 |
| LMArena Korean | 1260 | 1151 |
| LMArena Russian | 1324 | 1209 |
| LMArena Spanish | 1346 | 1234 |

## Instruction Following

- Mistral Small: 66.6 (#204)
- Phi-4: 60.6 (#246)

| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| LiveBench Instruction Following | 63.7% | 58.4% |
| LMArena Instruction Following | 1310 | 1201 |

## Long Context

- Mistral Small: 40.4 (#151)
- Phi-4: 36.9 (#221)

| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1327 | 1217 |

## Writing & Preference

- Mistral Small: 52.6 (#165)
- Phi-4: 40.7 (#239)

| Benchmark | Mistral Small | Phi-4 |
|---|---|---|
| LMArena Text | 1338 | 1217 |
| LMArena Creative Writing | 1304 | 1182 |
| LMArena Multi-Turn | 1344 | 1206 |
| LiveBench Language | 30.5% | 25.6% |
| Short-Story Creative Writing | — | 62.6% |

## FAQ

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

Mistral Small is the stronger model overall, scoring 33.1 to 30.9 on the Noometry Index. Phi-4 costs 3.0× less per token, which makes it the better buy when Mistral Small's lead doesn't matter for your workload.

### Which is cheaper, Mistral Small 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 lists at $0.15 and $0.60.

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

They score almost the same on coding (33.5 vs 33.8); test both on your own repository before choosing.

### Which has the bigger context window?

Mistral Small does, with 256K tokens against 128K.

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

32 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Phi-4 has 37.