# MiniMax-M2 vs Mistral Large 3

> Mistral Large 3 is the stronger model overall, scoring 39.1 to 37.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-vs-mistral-large-3
- Last updated: 2026-10-11
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. MiniMax-M2 scores higher in 3 categories and Mistral Large 3 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mistral Large 3 leads 52.5 to 45.3.
- The biggest single-benchmark swing is NYT Connections (extended): 14.8% for MiniMax-M2 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-M2.
- Mistral Large 3 accepts more context: 262K tokens versus 205K.

## Snapshot

| | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 37.4 | 39.1 |
| Rank | 204 | 176 |
| Context | 205K | 262K |
| Input $/M | $0.30 | $0.25 |
| Output $/M | $1.20 | $0.75 |
| Weights | Open | Open |

## Coding

- MiniMax-M2: 39.3 (#159)
- Mistral Large 3: 34.4 (#237)

| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1297 | 1230 |
| LMArena Coding | 1370 | 1448 |
| SWE-bench Verified (bash only) | 61% | — |

## Agentic & Tool Use

- MiniMax-M2: 25.1 (#109)
- Mistral Large 3: —

| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |

## Reasoning

- MiniMax-M2: 19.4 (#258)
- Mistral Large 3: 15.2 (#319)

| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 57.8% | 50.9% |
| NYT Connections (extended) | 14.8% | 7.5% |
| LMArena Hard Prompts | 1357 | 1429 |
| Thematic Generalization | — | 23% |

## Math

- MiniMax-M2: 37.3 (#160)
- Mistral Large 3: 38.7 (#129)

| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1352 | 1414 |

## Knowledge

- MiniMax-M2: 37.0 (#163)
- Mistral Large 3: 36.0 (#177)

| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1337 | 1421 |
| Vectara Hallucination Rate | — | 14.5% |

## Multimodal

- MiniMax-M2: —
- Mistral Large 3: 38.2 (#66)

| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |

## Multilingual

- MiniMax-M2: 45.3 (#171)
- Mistral Large 3: 52.5 (#84)

| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1313 | 1413 |
| LMArena Chinese | 1366 | 1447 |
| LMArena French | 1335 | 1455 |
| LMArena German | 1355 | 1437 |
| LMArena Russian | 1331 | 1411 |
| LMArena Spanish | 1326 | 1440 |
| LMArena Japanese | — | 1394 |
| LMArena Korean | — | 1384 |

## Instruction Following

- MiniMax-M2: 70.2 (#166)
- Mistral Large 3: 74.0 (#108)

| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1328 | 1403 |

## Long Context

- MiniMax-M2: 40.5 (#153)
- Mistral Large 3: 43.1 (#105)

| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1331 | 1413 |

## Writing & Preference

- MiniMax-M2: 53.0 (#162)
- Mistral Large 3: 60.0 (#101)

| Benchmark | MiniMax-M2 | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1340 | 1428 |
| LMArena Creative Writing | 1286 | 1386 |
| LMArena Multi-Turn | 1361 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |

## FAQ

### Is MiniMax-M2 better than Mistral Large 3?

Mistral Large 3 is the stronger model overall, scoring 39.1 to 37.4 on the Noometry Index.

### Which is cheaper, MiniMax-M2 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-M2 lists at $0.30 and $1.20.

### Is MiniMax-M2 or Mistral Large 3 better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 34.4 in the Noometry coding category.

### Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 205K.

### How many benchmarks do MiniMax-M2 and Mistral Large 3 share?

18 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Mistral Large 3 has 24.