# Llama 4 Scout vs MiMo-V2.5-Pro

> MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 27.4 on the Noometry Index. Llama 4 Scout costs 3.6× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/llama-4-scout-vs-mimo-v2-5-pro
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and MiMo-V2.5-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.5 to 37.1.
- The biggest single-benchmark swing is SciCode: 17% for Llama 4 Scout and 50.2% for MiMo-V2.5-Pro.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 128K.

## Snapshot

| | Llama 4 Scout | MiMo-V2.5-Pro |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 27.4 | 44.8 |
| Rank | 323 | 70 |
| Context | 128K | 1.05M |
| Input $/M | $0.10 | $0.43 |
| Output $/M | $0.30 | $0.87 |
| Weights | Open | Open |

## Coding

- Llama 4 Scout: 19.9 (#334)
- MiMo-V2.5-Pro: 47.0 (#58)

| Benchmark | Llama 4 Scout | MiMo-V2.5-Pro |
|---|---|---|
| SciCode | 17% | 50.2% |
| LMArena Coding | 1286 | 1502 |
| SWE-bench Verified (bash only) | 9.1% | — |
| LMArena WebDev | — | 1477 |
| BigCodeBench Complete | 43.1% | — |
| ALE-Bench | — | 899.8 |

## Agentic & Tool Use

- Llama 4 Scout: 24.4 (#109)
- MiMo-V2.5-Pro: —

| Benchmark | Llama 4 Scout | MiMo-V2.5-Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |

## Reasoning

- Llama 4 Scout: 9.2 (#339)
- MiMo-V2.5-Pro: 25.9 (#124)

| Benchmark | Llama 4 Scout | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 0% | 4% |
| LMArena Hard Prompts | 1266 | 1487 |
| DTBench | 57.9% | 84.5% |
| LMCA | 12% | 29.5% |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| NYT Connections (extended) | — | 34.4% |
| ARC-AGI-1 | 0.5% | — |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |

## Math

- Llama 4 Scout: 18.4 (#280)
- MiMo-V2.5-Pro: 38.6 (#84)

| Benchmark | Llama 4 Scout | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1286 | 1480 |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| ProofBench | — | 22% |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |

## Knowledge

- Llama 4 Scout: 31.8 (#208)
- MiMo-V2.5-Pro: 41.5 (#100)

| Benchmark | Llama 4 Scout | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1236 | 1501 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |

## Multimodal

- Llama 4 Scout: 31.6 (#98)
- MiMo-V2.5-Pro: —

| Benchmark | Llama 4 Scout | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |

## Multilingual

- Llama 4 Scout: 41.3 (#207)
- MiMo-V2.5-Pro: 55.3 (#33)

| Benchmark | Llama 4 Scout | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1253 | 1449 |
| LMArena Chinese | 1256 | 1507 |
| LMArena French | 1283 | 1489 |
| LMArena German | 1274 | 1455 |
| LMArena Japanese | 1209 | 1418 |
| LMArena Korean | 1207 | 1436 |
| LMArena Russian | 1263 | 1450 |
| LMArena Spanish | 1277 | 1470 |

## Instruction Following

- Llama 4 Scout: 66.0 (#212)
- MiMo-V2.5-Pro: 77.6 (#21)

| Benchmark | Llama 4 Scout | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1248 | 1477 |
| IFEval | 81.8% | — |

## Long Context

- Llama 4 Scout: 27.5 (#289)
- MiMo-V2.5-Pro: 45.4 (#38)

| Benchmark | Llama 4 Scout | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1265 | 1482 |
| Fiction.LiveBench | 36% | — |

## Writing & Preference

- Llama 4 Scout: 37.1 (#256)
- MiMo-V2.5-Pro: 65.5 (#47)

| Benchmark | Llama 4 Scout | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1279 | 1465 |
| LMArena Creative Writing | 1249 | 1440 |
| EQ-Bench Creative Writing | 783 | 1493 |
| LMArena Multi-Turn | 1281 | 1477 |
| WildBench | 78% | — |
| EQ-Bench 4 | — | 1208 |

## FAQ

### Is Llama 4 Scout better than MiMo-V2.5-Pro?

MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 27.4 on the Noometry Index. Llama 4 Scout costs 3.6× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.

### Which is cheaper, Llama 4 Scout or MiMo-V2.5-Pro?

Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.

### Is Llama 4 Scout or MiMo-V2.5-Pro better for coding?

MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 19.9 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5-Pro does, with 1.05M tokens against 128K.

### How many benchmarks do Llama 4 Scout and MiMo-V2.5-Pro share?

22 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and MiMo-V2.5-Pro has 27.