# Ministral 8B vs Phi-4 Mini

> Phi-4 Mini is the stronger model overall, scoring 30.9 to 28.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/ministral-8b-vs-phi-4-mini
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Ministral 8B scores higher in 1 category and Phi-4 Mini in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi-4 Mini leads 25.3 to 12.6.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 7.4% for Ministral 8B and 23.5% for Phi-4 Mini.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.15 / $0.15 for Ministral 8B.
- Ministral 8B accepts more context: 262K tokens versus 128K.

## Snapshot

| | Ministral 8B | Phi-4 Mini |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 28.2 | 30.9 |
| Rank | 325 | 283 |
| Context | 262K | 128K |
| Input $/M | $0.15 | $0.075 |
| Output $/M | $0.15 | $0.30 |
| Weights | Open | Open |

## Coding

- Ministral 8B: 35.0 (#230)
- Phi-4 Mini: 28.1 (#317)

| Benchmark | Ministral 8B | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
| LMArena Coding | 1202 | — |

## Agentic & Tool Use

- Ministral 8B: 16.4 (#148)
- Phi-4 Mini: —

| Benchmark | Ministral 8B | Phi-4 Mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |

## Reasoning

- Ministral 8B: 18.4 (#281)
- Phi-4 Mini: 22.4 (#195)

| Benchmark | Ministral 8B | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| LMArena Hard Prompts | 1191 | — |
| DTBench | 45.7% | — |

## Math

- Ministral 8B: 25.7 (#267)
- Phi-4 Mini: —

| Benchmark | Ministral 8B | Phi-4 Mini |
|---|---|---|
| LMArena Math | 1188 | — |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Ministral 8B: 12.6 (#297)
- Phi-4 Mini: 25.3 (#262)

| Benchmark | Ministral 8B | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | 7.4% | 23.5% |
| GPQA Diamond | 27.1% | — |
| LMArena Expert | 1170 | — |

## Multilingual

- Ministral 8B: 35.1 (#247)
- Phi-4 Mini: —

| Benchmark | Ministral 8B | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1165 | — |
| LMArena Chinese | 1193 | — |
| LMArena Russian | 1195 | — |

## Instruction Following

- Ministral 8B: 60.5 (#250)
- Phi-4 Mini: —

| Benchmark | Ministral 8B | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1161 | — |

## Long Context

- Ministral 8B: 36.7 (#227)
- Phi-4 Mini: —

| Benchmark | Ministral 8B | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1212 | — |

## Writing & Preference

- Ministral 8B: 39.6 (#246)
- Phi-4 Mini: —

| Benchmark | Ministral 8B | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1175 | — |
| LMArena Multi-Turn | 1166 | — |

## FAQ

### Is Ministral 8B better than Phi-4 Mini?

Phi-4 Mini is the stronger model overall, scoring 30.9 to 28.2 on the Noometry Index.

### Which is cheaper, Ministral 8B or Phi-4 Mini?

Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Ministral 8B lists at $0.15 and $0.15.

### Is Ministral 8B or Phi-4 Mini better for coding?

Ministral 8B scores higher on coding benchmarks: 35.0 versus 28.1 in the Noometry coding category.

### Which has the bigger context window?

Ministral 8B does, with 262K tokens against 128K.

### How many benchmarks do Ministral 8B and Phi-4 Mini share?

1 benchmark has published results for both models. Ministral 8B has 17 scored results on Noometry and Phi-4 Mini has 3.