# Mistral Large vs Qwen2.5-Max

> Qwen2.5-Max is the stronger model overall, scoring 40.7 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-large-vs-qwen2-5-max
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Mistral Large scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Max leads 36.9 to 18.2.
- The biggest single-benchmark swing is LiveBench Data Analysis: 50.1% for Mistral Large and 67.9% for Qwen2.5-Max.
- Mistral Large has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Large | Qwen2.5-Max |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.9 | 40.7 |
| Rank | 263 | 146 |
| Context | 131K | — |
| Input $/M | $2 | — |
| Output $/M | $6 | — |
| Weights | Open | Proprietary |

## Coding

- Mistral Large: 34.3 (#240)
- Qwen2.5-Max: 41.8 (#117)

| Benchmark | Mistral Large | Qwen2.5-Max |
|---|---|---|
| LiveBench Coding | 47.1% | 64.4% |
| LMArena Coding | 1277 | 1359 |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |

## Agentic & Tool Use

- Mistral Large: 28.6 (#89)
- Qwen2.5-Max: —

| Benchmark | Mistral Large | Qwen2.5-Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |

## Reasoning

- Mistral Large: 15.8 (#310)
- Qwen2.5-Max: 25.6 (#147)

| Benchmark | Mistral Large | Qwen2.5-Max |
|---|---|---|
| LiveBench Reasoning | 43.5% | 51.4% |
| LMArena Hard Prompts | 1257 | 1360 |
| LiveBench Data Analysis | 50.1% | 67.9% |
| Epoch Capabilities Index | 128.52 | 132.53 |
| LiveBench | 48.4% | 62.3% |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| DTBench | 65.1% | — |
| LMCA | 16.7% | — |
| ForecastBench | 57.1 | — |

## Math

- Mistral Large: 18.2 (#291)
- Qwen2.5-Max: 36.9 (#162)

| Benchmark | Mistral Large | Qwen2.5-Max |
|---|---|---|
| LiveBench Math | 42.5% | 58.4% |
| LMArena Math | 1262 | 1369 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |

## Knowledge

- Mistral Large: 30.1 (#230)
- Qwen2.5-Max: 35.3 (#186)

| Benchmark | Mistral Large | Qwen2.5-Max |
|---|---|---|
| Confabulations | 21.4% | 21.8% |
| LMArena Expert | 1232 | 1337 |
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |

## Multilingual

- Mistral Large: 40.0 (#219)
- Qwen2.5-Max: 48.1 (#146)

| Benchmark | Mistral Large | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1237 | 1352 |
| LMArena Chinese | 1240 | 1382 |
| LMArena French | 1325 | 1396 |
| LMArena German | 1254 | 1350 |
| LMArena Japanese | 1188 | 1300 |
| LMArena Korean | 1202 | 1304 |
| LMArena Russian | 1257 | 1353 |
| LMArena Spanish | 1268 | 1377 |

## Instruction Following

- Mistral Large: 67.9 (#191)
- Qwen2.5-Max: 71.3 (#152)

| Benchmark | Mistral Large | Qwen2.5-Max |
|---|---|---|
| LiveBench Instruction Following | 67.9% | 75.3% |
| LMArena Instruction Following | 1249 | 1335 |
| IFEval | 87.7% | — |

## Long Context

- Mistral Large: 38.3 (#199)
- Qwen2.5-Max: 41.4 (#142)

| Benchmark | Mistral Large | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1261 | 1358 |

## Writing & Preference

- Mistral Large: 40.7 (#242)
- Qwen2.5-Max: 55.4 (#146)

| Benchmark | Mistral Large | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1266 | 1367 |
| LMArena Creative Writing | 1243 | 1339 |
| Short-Story Creative Writing | 69% | 72.9% |
| LMArena Multi-Turn | 1260 | 1364 |
| LiveBench Language | 39.4% | 56.3% |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |

## FAQ

### Is Mistral Large better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 31.9 on the Noometry Index.

### Is Mistral Large or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 34.3 in the Noometry coding category.

### How many benchmarks do Mistral Large and Qwen2.5-Max share?

27 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen2.5-Max has 27.