# Llama 4 Scout vs MiniMax-M2.7

> MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 27.7 on the Noometry Index. Llama 4 Scout costs 3.5× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/llama-4-scout-vs-minimax-m2-7
- Last updated: 2026-10-12
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and MiniMax-M2.7 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.7 leads 58.9 to 37.0.
- The biggest single-benchmark swing is SciCode: 17% for Llama 4 Scout and 47% for MiniMax-M2.7.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
- MiniMax-M2.7 accepts more context: 205K tokens versus 128K.

## Snapshot

| | Llama 4 Scout | MiniMax-M2.7 |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 27.7 | 37.7 |
| Rank | 330 | 196 |
| Context | 128K | 205K |
| Input $/M | $0.10 | $0.30 |
| Output $/M | $0.30 | $1.20 |
| Weights | Open | Open |

## Coding

- Llama 4 Scout: 20.2 (#339)
- MiniMax-M2.7: 41.8 (#120)

| Benchmark | Llama 4 Scout | MiniMax-M2.7 |
|---|---|---|
| SciCode | 17% | 47% |
| LMArena Coding | 1286 | 1454 |
| SWE-bench Verified (bash only) | 9.1% | — |
| LMArena WebDev | — | 1398 |
| WeirdML | — | 37% |
| BigCodeBench Complete | 43.1% | — |
| ALE-Bench | — | 599.25 |

## Agentic & Tool Use

- Llama 4 Scout: 24.6 (#119)
- MiniMax-M2.7: 25.1 (#111)

| Benchmark | Llama 4 Scout | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| Berkeley Function Calling Leaderboard | 28.1% | — |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |

## Reasoning

- Llama 4 Scout: 9.1 (#345)
- MiniMax-M2.7: 19.7 (#253)

| Benchmark | Llama 4 Scout | MiniMax-M2.7 |
|---|---|---|
| CritPt | 0% | 0.6% |
| LMArena Hard Prompts | 1266 | 1422 |
| Epoch Capabilities Index | 129.64 | 145.85 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| NYT Connections (extended) | — | 24.7% |
| ARC-AGI-1 | 0.5% | — |
| Thematic Generalization | — | 39.3% |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| ForecastBench | 57.5 | — |

## Math

- Llama 4 Scout: 19.6 (#286)
- MiniMax-M2.7: 25.9 (#263)

| Benchmark | Llama 4 Scout | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1287 | 1420 |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| ProofBench | — | 3% |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |

## Knowledge

- Llama 4 Scout: 31.9 (#217)
- MiniMax-M2.7: 37.7 (#152)

| Benchmark | Llama 4 Scout | MiniMax-M2.7 |
|---|---|---|
| Vectara Hallucination Rate | 7.7% | 12.9% |
| LMArena Expert | 1235 | 1444 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| GPQA (HELM) | 50.7% | — |

## Multimodal

- Llama 4 Scout: 32.2 (#102)
- MiniMax-M2.7: —

| Benchmark | Llama 4 Scout | MiniMax-M2.7 |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |

## Multilingual

- Llama 4 Scout: 41.0 (#212)
- MiniMax-M2.7: 50.3 (#123)

| Benchmark | Llama 4 Scout | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1252 | 1382 |
| LMArena Chinese | 1255 | 1441 |
| LMArena French | 1282 | 1421 |
| LMArena German | 1272 | 1398 |
| LMArena Japanese | 1206 | 1262 |
| LMArena Korean | 1207 | 1313 |
| LMArena Russian | 1263 | 1383 |
| LMArena Spanish | 1278 | 1403 |

## Instruction Following

- Llama 4 Scout: 65.8 (#217)
- MiniMax-M2.7: 74.1 (#103)

| Benchmark | Llama 4 Scout | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1405 |
| IFEval | 81.8% | — |

## Long Context

- Llama 4 Scout: 27.5 (#294)
- MiniMax-M2.7: 43.3 (#99)

| Benchmark | Llama 4 Scout | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1265 | 1419 |
| Fiction.LiveBench | 36% | — |

## Writing & Preference

- Llama 4 Scout: 37.0 (#261)
- MiniMax-M2.7: 58.9 (#112)

| Benchmark | Llama 4 Scout | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1279 | 1405 |
| LMArena Creative Writing | 1249 | 1354 |
| LMArena Multi-Turn | 1280 | 1412 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |

## FAQ

### Is Llama 4 Scout better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 27.7 on the Noometry Index. Llama 4 Scout costs 3.5× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.

### Which is cheaper, Llama 4 Scout or MiniMax-M2.7?

Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.

### Is Llama 4 Scout or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 20.2 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.7 does, with 205K tokens against 128K.

### How many benchmarks do Llama 4 Scout and MiniMax-M2.7 share?

21 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and MiniMax-M2.7 has 30.