# Llama 4 Scout vs MiniMax-M3

> MiniMax-M3 is the stronger model overall, scoring 43.5 to 27.4 on the Noometry Index. Llama 4 Scout costs 3.5× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/llama-4-scout-vs-minimax-m3
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Llama 4 Scout scores higher in 1 category and MiniMax-M3 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 31.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.8% for Llama 4 Scout and 71.1% for MiniMax-M3.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 128K.

## Snapshot

| | Llama 4 Scout | MiniMax-M3 |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 27.4 | 43.5 |
| Rank | 323 | 81 |
| Context | 128K | 1M |
| Input $/M | $0.10 | $0.30 |
| Output $/M | $0.30 | $1.20 |
| Weights | Open | Open |

## Coding

- Llama 4 Scout: 19.9 (#334)
- MiniMax-M3: 41.5 (#111)

| Benchmark | Llama 4 Scout | MiniMax-M3 |
|---|---|---|
| SciCode | 17% | 47.1% |
| LMArena Coding | 1286 | 1470 |
| FrontierCode | — | 14.7% |
| SWE-bench Verified (bash only) | 9.1% | — |
| LMArena WebDev | — | 1482 |
| BigCodeBench Complete | 43.1% | — |
| ALE-Bench | — | 640.02 |

## Agentic & Tool Use

- Llama 4 Scout: 24.4 (#109)
- MiniMax-M3: 22.5 (#121)

| Benchmark | Llama 4 Scout | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| Berkeley Function Calling Leaderboard | 28.1% | — |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- Llama 4 Scout: 9.2 (#339)
- MiniMax-M3: 29.3 (#83)

| Benchmark | Llama 4 Scout | MiniMax-M3 |
|---|---|---|
| CritPt | 0% | 3.7% |
| LMArena Hard Prompts | 1266 | 1447 |
| DTBench | 57.9% | 78.9% |
| LMCA | 12% | 33.7% |
| Epoch Capabilities Index | 129.64 | 147 |
| ForecastBench | 57.5 | 61.4 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 45.8% |
| Kagi LLM Benchmark | 36.9% | — |
| NYT Connections (extended) | — | 65.1% |
| ARC-AGI-1 | 0.5% | — |
| Chess Puzzles | — | 14% |
| Mystery Game Puzzles | — | 8% |
| Surface Evolver Bench | — | 55% |

## Math

- Llama 4 Scout: 18.4 (#280)
- MiniMax-M3: 39.1 (#83)

| Benchmark | Llama 4 Scout | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 71.1% |
| LMArena Math | 1286 | 1432 |
| ProofBench | — | 18% |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |

## Knowledge

- Llama 4 Scout: 31.8 (#208)
- MiniMax-M3: 58.4 (#32)

| Benchmark | Llama 4 Scout | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 51.8% | 90.9% |
| LMArena Expert | 1236 | 1462 |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |

## Multimodal

- Llama 4 Scout: 31.6 (#98)
- MiniMax-M3: 39.5 (#45)

| Benchmark | Llama 4 Scout | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1118 | 1254 |
| LMArena Document | — | 1435 |
| SpatialViz-Bench | 34.2% | — |

## Multilingual

- Llama 4 Scout: 41.3 (#207)
- MiniMax-M3: 53.2 (#70)

| Benchmark | Llama 4 Scout | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1253 | 1420 |
| LMArena Chinese | 1256 | 1465 |
| LMArena French | 1283 | 1445 |
| LMArena German | 1274 | 1424 |
| LMArena Japanese | 1209 | 1381 |
| LMArena Korean | 1207 | 1372 |
| LMArena Russian | 1263 | 1430 |
| LMArena Spanish | 1277 | 1431 |

## Instruction Following

- Llama 4 Scout: 66.0 (#212)
- MiniMax-M3: 75.7 (#56)

| Benchmark | Llama 4 Scout | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1433 |
| IFEval | 81.8% | — |

## Long Context

- Llama 4 Scout: 27.5 (#289)
- MiniMax-M3: 44.2 (#68)

| Benchmark | Llama 4 Scout | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1265 | 1445 |
| Fiction.LiveBench | 36% | — |

## Writing & Preference

- Llama 4 Scout: 37.1 (#256)
- MiniMax-M3: 62.3 (#79)

| Benchmark | Llama 4 Scout | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1279 | 1433 |
| LMArena Creative Writing | 1249 | 1405 |
| LMArena Multi-Turn | 1281 | 1441 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
| EQ-Bench 4 | — | 1150 |

## FAQ

### Is Llama 4 Scout better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.5 to 27.4 on the Noometry Index. Llama 4 Scout costs 3.5× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.

### Which is cheaper, Llama 4 Scout or MiniMax-M3?

Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.

### Is Llama 4 Scout or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 19.9 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 128K.

### How many benchmarks do Llama 4 Scout and MiniMax-M3 share?

26 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and MiniMax-M3 has 41.