# MiniMax-M2.1 vs Mistral Small

> MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 33.4 on the Noometry Index. Mistral Small costs 2.0× 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
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. MiniMax-M2.1 scores higher in 7 categories and Mistral Small in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2.1 leads 38.3 to 16.4.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 11.8% for MiniMax-M2.1 and 5.1% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- Mistral Small accepts more context: 262K tokens versus 205K.

## Snapshot

| | MiniMax-M2.1 | Mistral Small |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 38.9 | 33.4 |
| Rank | 178 | 243 |
| Context | 205K | 262K |
| Input $/M | $0.30 | $0.15 |
| Output $/M | $1.20 | $0.60 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.1: 40.4 (#143)
- Mistral Small: 34.0 (#247)

| Benchmark | MiniMax-M2.1 | Mistral Small |
|---|---|---|
| LMArena Coding | 1421 | 1362 |
| ALE-Bench | 623.83 | 497.62 |
| LMArena WebDev | 1384 | — |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |

## Agentic & Tool Use

- MiniMax-M2.1: 27.9 (#98)
- Mistral Small: 28.1 (#93)

| Benchmark | MiniMax-M2.1 | Mistral Small |
|---|---|---|
| Terminal-Bench | 36.6% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- MiniMax-M2.1: 16.6 (#302)
- Mistral Small: 19.8 (#250)

| Benchmark | MiniMax-M2.1 | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1335 |
| Kagi LLM Benchmark | — | 37.8% |
| NYT Connections (extended) | 11.2% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |

## Math

- MiniMax-M2.1: 38.3 (#138)
- Mistral Small: 16.4 (#293)

| Benchmark | MiniMax-M2.1 | Mistral Small |
|---|---|---|
| LMArena Math | 1397 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |

## Knowledge

- MiniMax-M2.1: 38.3 (#147)
- Mistral Small: 31.0 (#222)

| Benchmark | MiniMax-M2.1 | Mistral Small |
|---|---|---|
| Vectara Hallucination Rate | 11.8% | 5.1% |
| LMArena Expert | 1431 | 1291 |
| GPQA Diamond | — | 47.5% |
| MMLU | — | 68.7% |

## Multimodal

- MiniMax-M2.1: —
- Mistral Small: 33.5 (#96)

| Benchmark | MiniMax-M2.1 | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |

## Multilingual

- MiniMax-M2.1: 50.0 (#128)
- Mistral Small: 45.5 (#169)

| Benchmark | MiniMax-M2.1 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1378 | 1315 |
| LMArena Chinese | 1430 | 1340 |
| LMArena French | 1404 | 1337 |
| LMArena German | 1381 | 1340 |
| LMArena Japanese | 1287 | 1275 |
| LMArena Korean | 1298 | 1259 |
| LMArena Russian | 1387 | 1324 |
| LMArena Spanish | 1397 | 1346 |

## Instruction Following

- MiniMax-M2.1: 73.8 (#112)
- Mistral Small: 66.4 (#209)

| Benchmark | MiniMax-M2.1 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1400 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- MiniMax-M2.1: 43.2 (#101)
- Mistral Small: 40.4 (#156)

| Benchmark | MiniMax-M2.1 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1416 | 1327 |

## Writing & Preference

- MiniMax-M2.1: 58.3 (#120)
- Mistral Small: 52.5 (#171)

| Benchmark | MiniMax-M2.1 | Mistral Small |
|---|---|---|
| LMArena Text | 1392 | 1338 |
| LMArena Creative Writing | 1361 | 1305 |
| LMArena Multi-Turn | 1396 | 1344 |
| LiveBench Language | — | 30.5% |

## FAQ

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

MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 33.4 on the Noometry Index. Mistral Small costs 2.0× 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?

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.

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

MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 34.0 in the Noometry coding category.

### Which has the bigger context window?

Mistral Small does, with 262K tokens against 205K.

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

19 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Mistral Small has 39.