# Llama 4 Scout vs Ministral 3B

> Llama 4 Scout is the stronger model overall, scoring 27.7 to 26.2 on the Noometry Index. Ministral 3B costs 1.5× less per token, which makes it the better buy when Llama 4 Scout's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/llama-4-scout-vs-ministral-3b
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Llama 4 Scout scores higher in 1 category and Ministral 3B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 4 Scout leads 31.9 to 10.4.
- The biggest single-benchmark swing is MATH Level 5: 62.3% for Llama 4 Scout and 14.4% for Ministral 3B.
- Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.10 / $0.30 for Llama 4 Scout.
- Ministral 3B accepts more context: 131K tokens versus 128K.

## Snapshot

| | Llama 4 Scout | Ministral 3B |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 27.7 | 26.2 |
| Rank | 330 | 338 |
| Context | 128K | 131K |
| Input $/M | $0.10 | $0.10 |
| Output $/M | $0.30 | $0.10 |
| Weights | Open | Open |

## Coding

- Llama 4 Scout: 20.2 (#339)
- Ministral 3B: —

| Benchmark | Llama 4 Scout | Ministral 3B |
|---|---|---|
| SWE-bench Verified (bash only) | 9.1% | — |
| SciCode | 17% | — |
| LMArena Coding | 1286 | — |
| BigCodeBench Complete | 43.1% | — |

## Agentic & Tool Use

- Llama 4 Scout: 24.6 (#119)
- Ministral 3B: —

| Benchmark | Llama 4 Scout | Ministral 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |

## Reasoning

- Llama 4 Scout: 9.1 (#345)
- Ministral 3B: 18.4 (#282)

| Benchmark | Llama 4 Scout | Ministral 3B |
|---|---|---|
| DTBench | 57.9% | 51.7% |
| LMCA | 12% | 5.5% |
| Epoch Capabilities Index | 129.64 | 118.1 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | 1266 | — |
| ForecastBench | 57.5 | — |

## Math

- Llama 4 Scout: 19.6 (#286)
- Ministral 3B: 26.6 (#258)

| Benchmark | Llama 4 Scout | Ministral 3B |
|---|---|---|
| MATH Level 5 | 62.3% | 14.4% |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| Omni-MATH | 37.3% | — |
| LMArena Math | 1287 | — |
| FrontierMath (Feb 2025 set) | 0% | — |

## Knowledge

- Llama 4 Scout: 31.9 (#217)
- Ministral 3B: 10.4 (#302)

| Benchmark | Llama 4 Scout | Ministral 3B |
|---|---|---|
| GPQA Diamond | 51.8% | 25.3% |
| Vectara Hallucination Rate | 7.7% | 7.3% |
| MMLU-Pro | 74.2% | — |
| GPQA (HELM) | 50.7% | — |
| LMArena Expert | 1235 | — |

## Multimodal

- Llama 4 Scout: 32.2 (#102)
- Ministral 3B: —

| Benchmark | Llama 4 Scout | Ministral 3B |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |

## Multilingual

- Llama 4 Scout: 41.0 (#212)
- Ministral 3B: —

| Benchmark | Llama 4 Scout | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1252 | — |
| LMArena Chinese | 1255 | — |
| LMArena French | 1282 | — |
| LMArena German | 1272 | — |
| LMArena Japanese | 1206 | — |
| LMArena Korean | 1207 | — |
| LMArena Russian | 1263 | — |
| LMArena Spanish | 1278 | — |

## Instruction Following

- Llama 4 Scout: 65.8 (#217)
- Ministral 3B: —

| Benchmark | Llama 4 Scout | Ministral 3B |
|---|---|---|
| IFEval | 81.8% | — |
| LMArena Instruction Following | 1248 | — |

## Long Context

- Llama 4 Scout: 27.5 (#294)
- Ministral 3B: —

| Benchmark | Llama 4 Scout | Ministral 3B |
|---|---|---|
| Fiction.LiveBench | 36% | — |
| LMArena Longer Query | 1265 | — |

## Writing & Preference

- Llama 4 Scout: 37.0 (#261)
- Ministral 3B: —

| Benchmark | Llama 4 Scout | Ministral 3B |
|---|---|---|
| LMArena Text | 1279 | — |
| LMArena Creative Writing | 1249 | — |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
| LMArena Multi-Turn | 1280 | — |

## FAQ

### Is Llama 4 Scout better than Ministral 3B?

Llama 4 Scout is the stronger model overall, scoring 27.7 to 26.2 on the Noometry Index. Ministral 3B costs 1.5× less per token, which makes it the better buy when Llama 4 Scout's lead doesn't matter for your workload.

### Which is cheaper, Llama 4 Scout or Ministral 3B?

Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Llama 4 Scout lists at $0.10 and $0.30.

### Which has the bigger context window?

Ministral 3B does, with 131K tokens against 128K.

### How many benchmarks do Llama 4 Scout and Ministral 3B share?

6 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Ministral 3B has 6.