# MiniMax-M3 vs Mistral Large 3

> MiniMax-M3 is the stronger model overall, scoring 43.8 to 39.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m3-vs-mistral-large-3
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. MiniMax-M3 scores higher in 9 categories and Mistral Large 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 36.0.
- The biggest single-benchmark swing is NYT Connections (extended): 65.1% for MiniMax-M3 and 7.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 262K.

## Snapshot

| | MiniMax-M3 | Mistral Large 3 |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 43.8 | 39.1 |
| Rank | 85 | 176 |
| Context | 1M | 262K |
| Input $/M | $0.30 | $0.25 |
| Output $/M | $1.20 | $0.75 |
| Weights | Open | Open |

## Coding

- MiniMax-M3: 41.8 (#118)
- Mistral Large 3: 34.4 (#237)

| Benchmark | MiniMax-M3 | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1482 | 1230 |
| LMArena Coding | 1469 | 1448 |
| FrontierCode | 14.7% | — |
| SciCode | 47.1% | — |
| ALE-Bench | 640.02 | — |

## Agentic & Tool Use

- MiniMax-M3: 22.6 (#130)
- Mistral Large 3: —

| Benchmark | MiniMax-M3 | Mistral Large 3 |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |

## Reasoning

- MiniMax-M3: 30.1 (#87)
- Mistral Large 3: 15.2 (#319)

| Benchmark | MiniMax-M3 | Mistral Large 3 |
|---|---|---|
| NYT Connections (extended) | 65.1% | 7.5% |
| LMArena Hard Prompts | 1447 | 1429 |
| SimpleBench | 45.8% | — |
| Kagi LLM Benchmark | — | 50.9% |
| CritPt | 3.7% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | — | 23% |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| Epoch Capabilities Index | 146.95 | — |
| ForecastBench | 61.4 | — |

## Math

- MiniMax-M3: 40.0 (#95)
- Mistral Large 3: 38.7 (#129)

| Benchmark | MiniMax-M3 | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1429 | 1414 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |

## Knowledge

- MiniMax-M3: 58.4 (#35)
- Mistral Large 3: 36.0 (#177)

| Benchmark | MiniMax-M3 | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1461 | 1421 |
| GPQA Diamond | 90.9% | — |
| Vectara Hallucination Rate | — | 14.5% |

## Multimodal

- MiniMax-M3: 40.2 (#51)
- Mistral Large 3: 38.2 (#66)

| Benchmark | MiniMax-M3 | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1253 | 1221 |
| LMArena Document | 1435 | — |

## Multilingual

- MiniMax-M3: 53.0 (#75)
- Mistral Large 3: 52.5 (#84)

| Benchmark | MiniMax-M3 | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1420 | 1413 |
| LMArena Chinese | 1463 | 1447 |
| LMArena French | 1447 | 1455 |
| LMArena German | 1426 | 1437 |
| LMArena Japanese | 1381 | 1394 |
| LMArena Korean | 1372 | 1384 |
| LMArena Russian | 1428 | 1411 |
| LMArena Spanish | 1432 | 1440 |

## Instruction Following

- MiniMax-M3: 75.5 (#62)
- Mistral Large 3: 74.0 (#108)

| Benchmark | MiniMax-M3 | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1433 | 1403 |

## Long Context

- MiniMax-M3: 44.2 (#72)
- Mistral Large 3: 43.1 (#105)

| Benchmark | MiniMax-M3 | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1445 | 1413 |

## Writing & Preference

- MiniMax-M3: 62.1 (#83)
- Mistral Large 3: 60.0 (#101)

| Benchmark | MiniMax-M3 | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1433 | 1428 |
| LMArena Creative Writing | 1404 | 1386 |
| LMArena Multi-Turn | 1442 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
| EQ-Bench 4 | 1150 | — |

## FAQ

### Is MiniMax-M3 better than Mistral Large 3?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 39.1 on the Noometry Index.

### Which is cheaper, MiniMax-M3 or Mistral Large 3?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.

### Is MiniMax-M3 or Mistral Large 3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 34.4 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 262K.

### How many benchmarks do MiniMax-M3 and Mistral Large 3 share?

20 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Mistral Large 3 has 24.