# MiniMax-M2.1 vs Mistral Large

> MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-1-vs-mistral-large
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. MiniMax-M2.1 scores higher in 8 categories and Mistral Large in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2.1 leads 38.3 to 18.2.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 11.8% for MiniMax-M2.1 and 4.5% for Mistral Large.
- MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $6 for Mistral Large.
- MiniMax-M2.1 accepts more context: 205K tokens versus 131K.

## Snapshot

| | MiniMax-M2.1 | Mistral Large |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 38.9 | 31.9 |
| Rank | 178 | 263 |
| Context | 205K | 131K |
| Input $/M | $0.30 | $2 |
| Output $/M | $1.20 | $6 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.1: 40.4 (#143)
- Mistral Large: 34.3 (#240)

| Benchmark | MiniMax-M2.1 | Mistral Large |
|---|---|---|
| LMArena Coding | 1421 | 1277 |
| ALE-Bench | 623.83 | 264.7 |
| LMArena WebDev | 1384 | — |
| SciCode | — | 36.2% |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |

## Agentic & Tool Use

- MiniMax-M2.1: 27.9 (#98)
- Mistral Large: 28.6 (#89)

| Benchmark | MiniMax-M2.1 | Mistral Large |
|---|---|---|
| Terminal-Bench | 36.6% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |

## Reasoning

- MiniMax-M2.1: 16.6 (#302)
- Mistral Large: 15.8 (#310)

| Benchmark | MiniMax-M2.1 | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1257 |
| SimpleBench | — | 22.5% |
| NYT Connections (extended) | 11.2% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Epoch Capabilities Index | — | 128.52 |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |

## Math

- MiniMax-M2.1: 38.3 (#138)
- Mistral Large: 18.2 (#291)

| Benchmark | MiniMax-M2.1 | Mistral Large |
|---|---|---|
| LMArena Math | 1397 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- MiniMax-M2.1: 38.3 (#147)
- Mistral Large: 30.1 (#230)

| Benchmark | MiniMax-M2.1 | Mistral Large |
|---|---|---|
| Vectara Hallucination Rate | 11.8% | 4.5% |
| LMArena Expert | 1431 | 1232 |
| GPQA Diamond | — | 51.3% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |

## Multilingual

- MiniMax-M2.1: 50.0 (#128)
- Mistral Large: 40.0 (#219)

| Benchmark | MiniMax-M2.1 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1378 | 1237 |
| LMArena Chinese | 1430 | 1240 |
| LMArena French | 1404 | 1325 |
| LMArena German | 1381 | 1254 |
| LMArena Japanese | 1287 | 1188 |
| LMArena Korean | 1298 | 1202 |
| LMArena Russian | 1387 | 1257 |
| LMArena Spanish | 1397 | 1268 |

## Instruction Following

- MiniMax-M2.1: 73.8 (#112)
- Mistral Large: 67.9 (#191)

| Benchmark | MiniMax-M2.1 | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1400 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |

## Long Context

- MiniMax-M2.1: 43.2 (#101)
- Mistral Large: 38.3 (#199)

| Benchmark | MiniMax-M2.1 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1416 | 1261 |

## Writing & Preference

- MiniMax-M2.1: 58.3 (#120)
- Mistral Large: 40.7 (#242)

| Benchmark | MiniMax-M2.1 | Mistral Large |
|---|---|---|
| LMArena Text | 1392 | 1266 |
| LMArena Creative Writing | 1361 | 1243 |
| LMArena Multi-Turn | 1396 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |

## FAQ

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

MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 31.9 on the Noometry Index.

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

MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Mistral Large lists at $2 and $6.

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

MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 34.3 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.1 does, with 205K tokens against 131K.

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

19 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Mistral Large has 51.