# MiniMax-M2.1 vs Mistral Small 3

> MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 30.9 on the Noometry Index. Mistral Small 3 costs 9.1× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/minimax-m2-1-vs-mistral-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. MiniMax-M2.1 scores higher in 7 categories and Mistral Small 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.5 to 32.4.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- MiniMax-M2.1 accepts more context: 205K tokens versus 33K.

## Snapshot

| | MiniMax-M2.1 | Mistral Small 3 |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 38.4 | 30.9 |
| Rank | 177 | 268 |
| Context | 205K | 33K |
| Input $/M | $0.30 | $0.05 |
| Output $/M | $1.20 | $0.08 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.1: 40.1 (#132)
- Mistral Small 3: 36.0 (#203)

| Benchmark | MiniMax-M2.1 | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1421 | 1246 |
| LMArena WebDev | 1384 | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
| ALE-Bench | 623.83 | — |

## Agentic & Tool Use

- MiniMax-M2.1: 27.7 (#91)
- Mistral Small 3: —

| Benchmark | MiniMax-M2.1 | Mistral Small 3 |
|---|---|---|
| Terminal-Bench | 36.6% | — |

## Reasoning

- MiniMax-M2.1: 15.8 (#301)
- Mistral Small 3: 18.2 (#269)

| Benchmark | MiniMax-M2.1 | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1410 | 1233 |
| NYT Connections (extended) | 11.2% | — |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.06 |

## Math

- MiniMax-M2.1: 35.6 (#142)
- Mistral Small 3: 15.3 (#290)

| Benchmark | MiniMax-M2.1 | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1396 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |

## Knowledge

- MiniMax-M2.1: 37.7 (#143)
- Mistral Small 3: 25.0 (#258)

| Benchmark | MiniMax-M2.1 | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1432 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |
| Vectara Hallucination Rate | 11.8% | — |

## Multilingual

- MiniMax-M2.1: 50.2 (#123)
- Mistral Small 3: 37.5 (#231)

| Benchmark | MiniMax-M2.1 | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1378 | 1198 |
| LMArena Chinese | 1430 | 1204 |
| LMArena French | 1405 | 1202 |
| LMArena German | 1380 | 1211 |
| LMArena Japanese | 1287 | 1111 |
| LMArena Korean | 1297 | 1188 |
| LMArena Russian | 1386 | 1216 |
| LMArena Spanish | 1396 | — |

## Instruction Following

- MiniMax-M2.1: 74.0 (#108)
- Mistral Small 3: 63.9 (#224)

| Benchmark | MiniMax-M2.1 | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1399 | 1214 |

## Long Context

- MiniMax-M2.1: 43.2 (#98)
- Mistral Small 3: 37.8 (#206)

| Benchmark | MiniMax-M2.1 | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1416 | 1246 |

## Writing & Preference

- MiniMax-M2.1: 58.5 (#114)
- Mistral Small 3: 32.4 (#275)

| Benchmark | MiniMax-M2.1 | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1392 | 1234 |
| LMArena Creative Writing | 1362 | 1195 |
| LMArena Multi-Turn | 1396 | 1217 |
| EQ-Bench Creative Writing | — | 707 |

## FAQ

### Is MiniMax-M2.1 better than Mistral Small 3?

MiniMax-M2.1 is the stronger model overall, scoring 38.4 to 30.9 on the Noometry Index. Mistral Small 3 costs 9.1× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.

### Which is cheaper, MiniMax-M2.1 or Mistral Small 3?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.

### Is MiniMax-M2.1 or Mistral Small 3 better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.1 versus 36.0 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.1 does, with 205K tokens against 33K.

### How many benchmarks do MiniMax-M2.1 and Mistral Small 3 share?

16 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Mistral Small 3 has 24.