# Mistral Medium 3.5 vs Phi-4

> Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 30.9 on the Noometry Index. Phi-4 costs 34× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-medium-3-5-vs-phi-4
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 7 categories and Phi-4 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium 3.5 leads 58.6 to 40.7.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 128K.

## Snapshot

| | Mistral Medium 3.5 | Phi-4 |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 39.6 | 30.9 |
| Rank | 151 | 269 |
| Context | 262K | 128K |
| Input $/M | $1.50 | $0.07 |
| Output $/M | $7.50 | $0.14 |
| Weights | Open | Open |

## Coding

- Mistral Medium 3.5: 35.7 (#208)
- Phi-4: 33.8 (#237)

| Benchmark | Mistral Medium 3.5 | Phi-4 |
|---|---|---|
| LMArena Coding | 1461 | 1231 |
| LMArena WebDev | 1263 | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |

## Agentic & Tool Use

- Mistral Medium 3.5: —
- Phi-4: 22.6 (#120)

| Benchmark | Mistral Medium 3.5 | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |

## Reasoning

- Mistral Medium 3.5: 16.6 (#290)
- Phi-4: 17.0 (#287)

| Benchmark | Mistral Medium 3.5 | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1436 | 1220 |
| Epoch Capabilities Index | 141.42 | 130.43 |
| Kagi LLM Benchmark | 41.4% | — |
| NYT Connections (extended) | 12.9% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| LiveBench | — | 41.6% |

## Math

- Mistral Medium 3.5: 36.4 (#113)
- Phi-4: 19.6 (#279)

| Benchmark | Mistral Medium 3.5 | Phi-4 |
|---|---|---|
| LMArena Math | 1432 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |

## Knowledge

- Mistral Medium 3.5: 39.3 (#123)
- Phi-4: 32.5 (#204)

| Benchmark | Mistral Medium 3.5 | Phi-4 |
|---|---|---|
| LMArena Expert | 1431 | 1203 |
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| MMLU | — | 84.8% |

## Multimodal

- Mistral Medium 3.5: 37.6 (#64)
- Phi-4: —

| Benchmark | Mistral Medium 3.5 | Phi-4 |
|---|---|---|
| LMArena Vision | 1222 | — |

## Multilingual

- Mistral Medium 3.5: 52.1 (#93)
- Phi-4: 37.4 (#232)

| Benchmark | Mistral Medium 3.5 | Phi-4 |
|---|---|---|
| LMArena Non-English | 1405 | 1197 |
| LMArena Chinese | 1443 | 1211 |
| LMArena French | 1448 | 1223 |
| LMArena German | 1453 | 1222 |
| LMArena Korean | 1387 | 1151 |
| LMArena Russian | 1396 | 1209 |
| LMArena Spanish | 1406 | 1234 |
| LMArena Japanese | — | 1158 |

## Instruction Following

- Mistral Medium 3.5: 74.7 (#87)
- Phi-4: 60.6 (#246)

| Benchmark | Mistral Medium 3.5 | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1414 | 1201 |
| LiveBench Instruction Following | — | 58.4% |

## Long Context

- Mistral Medium 3.5: 43.2 (#101)
- Phi-4: 36.9 (#221)

| Benchmark | Mistral Medium 3.5 | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1414 | 1217 |

## Writing & Preference

- Mistral Medium 3.5: 58.6 (#113)
- Phi-4: 40.7 (#239)

| Benchmark | Mistral Medium 3.5 | Phi-4 |
|---|---|---|
| LMArena Text | 1421 | 1217 |
| LMArena Creative Writing | 1372 | 1182 |
| LMArena Multi-Turn | 1423 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| EQ-Bench 4 | 993 | — |
| LiveBench Language | — | 25.6% |

## FAQ

### Is Mistral Medium 3.5 better than Phi-4?

Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 30.9 on the Noometry Index. Phi-4 costs 34× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

### Which is cheaper, Mistral Medium 3.5 or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is Mistral Medium 3.5 or Phi-4 better for coding?

Mistral Medium 3.5 scores higher on coding benchmarks: 35.7 versus 33.8 in the Noometry coding category.

### Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 128K.

### How many benchmarks do Mistral Medium 3.5 and Phi-4 share?

17 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Phi-4 has 37.