# Mistral 7B vs Phi-4

> Phi-4 is the stronger model overall, scoring 31.2 to 23.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-7b-vs-phi-4
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Phi-4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi-4 leads 32.6 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 3.7% for Mistral 7B and 64.9% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.25 / $0.25 for Mistral 7B.
- Phi-4 accepts more context: 128K tokens versus 8K.

## Snapshot

| | Mistral 7B | Phi-4 |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 23.0 | 31.2 |
| Rank | 351 | 279 |
| Context | 8K | 128K |
| Input $/M | $0.25 | $0.07 |
| Output $/M | $0.25 | $0.14 |
| Weights | Open | Open |

## Coding

- Mistral 7B: 26.4 (#326)
- Phi-4: 34.4 (#239)

| Benchmark | Mistral 7B | Phi-4 |
|---|---|---|
| BigCodeBench Instruct | 19.5% | 45.5% |
| LMArena Coding | 1082 | 1231 |
| BigCodeBench Complete | 27.3% | 55.4% |
| LiveBench Coding | — | 30.7% |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |

## Agentic & Tool Use

- Mistral 7B: —
- Phi-4: 22.8 (#128)

| Benchmark | Mistral 7B | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |

## Reasoning

- Mistral 7B: 13.1 (#336)
- Phi-4: 17.7 (#291)

| Benchmark | Mistral 7B | Phi-4 |
|---|---|---|
| Chess Puzzles | 0% | 1% |
| LMArena Hard Prompts | 1067 | 1220 |
| Epoch Capabilities Index | 112.21 | 130.42 |
| LiveBench Reasoning | — | 47.8% |
| DTBench | 42.5% | — |
| LiveBench Data Analysis | — | 45.2% |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| HellaSwag | 81% | — |
| LiveBench | — | 41.6% |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |

## Math

- Mistral 7B: 8.1 (#325)
- Phi-4: 20.8 (#285)

| Benchmark | Mistral 7B | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.3% | 13.8% |
| LMArena Math | 1085 | 1246 |
| MATH Level 5 | 3.7% | 64.9% |
| LiveBench Math | — | 42% |
| GSM8K | 54.4% | — |

## Knowledge

- Mistral 7B: 7.4 (#311)
- Phi-4: 32.6 (#209)

| Benchmark | Mistral 7B | Phi-4 |
|---|---|---|
| GPQA Diamond | 15.2% | 56.1% |
| LMArena Expert | 1036 | 1203 |
| MMLU | 62.5% | 84.8% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |

## Multilingual

- Mistral 7B: 25.8 (#283)
- Phi-4: 37.2 (#237)

| Benchmark | Mistral 7B | Phi-4 |
|---|---|---|
| LMArena Non-English | 1012 | 1197 |
| LMArena Chinese | 1009 | 1212 |
| LMArena French | 1037 | 1224 |
| LMArena German | 987 | 1222 |
| LMArena Japanese | 878 | 1158 |
| LMArena Russian | 1018 | 1209 |
| LMArena Spanish | 1026 | 1234 |
| LMArena Korean | — | 1151 |

## Instruction Following

- Mistral 7B: 54.2 (#280)
- Phi-4: 60.4 (#251)

| Benchmark | Mistral 7B | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1060 | 1201 |
| LiveBench Instruction Following | — | 58.4% |

## Long Context

- Mistral 7B: 32.2 (#271)
- Phi-4: 36.9 (#226)

| Benchmark | Mistral 7B | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1060 | 1217 |

## Writing & Preference

- Mistral 7B: 30.7 (#286)
- Phi-4: 40.5 (#244)

| Benchmark | Mistral 7B | Phi-4 |
|---|---|---|
| LMArena Text | 1090 | 1217 |
| LMArena Creative Writing | 1068 | 1182 |
| LMArena Multi-Turn | 1062 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| LiveBench Language | — | 25.6% |

## FAQ

### Is Mistral 7B better than Phi-4?

Phi-4 is the stronger model overall, scoring 31.2 to 23.0 on the Noometry Index.

### Which is cheaper, Mistral 7B or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Mistral 7B lists at $0.25 and $0.25.

### Is Mistral 7B or Phi-4 better for coding?

Phi-4 scores higher on coding benchmarks: 34.4 versus 26.4 in the Noometry coding category.

### Which has the bigger context window?

Phi-4 does, with 128K tokens against 8K.

### How many benchmarks do Mistral 7B and Phi-4 share?

24 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Phi-4 has 37.