# Mistral Small vs Qwen2.5-Max

> Qwen2.5-Max is the stronger model overall, scoring 40.7 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-small-vs-qwen2-5-max
- Last updated: 2026-10-11
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Mistral Small 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 16.4.
- The biggest single-benchmark swing is LiveBench Coding: 36.2% for Mistral Small and 64.4% for Qwen2.5-Max.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Small | Qwen2.5-Max |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 40.7 |
| Rank | 243 | 146 |
| Context | 262K | — |
| Input $/M | $0.15 | — |
| Output $/M | $0.60 | — |
| Weights | Open | Proprietary |

## Coding

- Mistral Small: 34.0 (#247)
- Qwen2.5-Max: 41.8 (#117)

| Benchmark | Mistral Small | Qwen2.5-Max |
|---|---|---|
| LiveBench Coding | 36.2% | 64.4% |
| LMArena Coding | 1362 | 1359 |
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |

## Agentic & Tool Use

- Mistral Small: 28.1 (#93)
- Qwen2.5-Max: —

| Benchmark | Mistral Small | Qwen2.5-Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |

## Reasoning

- Mistral Small: 19.8 (#250)
- Qwen2.5-Max: 25.6 (#147)

| Benchmark | Mistral Small | Qwen2.5-Max |
|---|---|---|
| LiveBench Reasoning | 44.8% | 51.4% |
| LMArena Hard Prompts | 1335 | 1360 |
| LiveBench Data Analysis | 53.7% | 67.9% |
| LiveBench | 44% | 62.3% |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| DTBench | 70.9% | — |
| LMCA | 20.6% | — |
| Epoch Capabilities Index | — | 132.53 |

## Math

- Mistral Small: 16.4 (#293)
- Qwen2.5-Max: 36.9 (#162)

| Benchmark | Mistral Small | Qwen2.5-Max |
|---|---|---|
| LiveBench Math | 39.9% | 58.4% |
| LMArena Math | 1341 | 1369 |
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| MATH Level 5 | 46.8% | — |

## Knowledge

- Mistral Small: 31.0 (#222)
- Qwen2.5-Max: 35.3 (#186)

| Benchmark | Mistral Small | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1291 | 1337 |
| GPQA Diamond | 47.5% | — |
| Confabulations | — | 21.8% |
| Vectara Hallucination Rate | 5.1% | — |
| MMLU | 68.7% | — |

## Multimodal

- Mistral Small: 33.5 (#96)
- Qwen2.5-Max: —

| Benchmark | Mistral Small | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1142 | — |

## Multilingual

- Mistral Small: 45.5 (#169)
- Qwen2.5-Max: 48.1 (#146)

| Benchmark | Mistral Small | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1315 | 1352 |
| LMArena Chinese | 1340 | 1382 |
| LMArena French | 1337 | 1396 |
| LMArena German | 1340 | 1350 |
| LMArena Japanese | 1275 | 1300 |
| LMArena Korean | 1259 | 1304 |
| LMArena Russian | 1324 | 1353 |
| LMArena Spanish | 1346 | 1377 |

## Instruction Following

- Mistral Small: 66.4 (#209)
- Qwen2.5-Max: 71.3 (#152)

| Benchmark | Mistral Small | Qwen2.5-Max |
|---|---|---|
| LiveBench Instruction Following | 63.7% | 75.3% |
| LMArena Instruction Following | 1310 | 1335 |

## Long Context

- Mistral Small: 40.4 (#156)
- Qwen2.5-Max: 41.4 (#142)

| Benchmark | Mistral Small | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1327 | 1358 |

## Writing & Preference

- Mistral Small: 52.5 (#171)
- Qwen2.5-Max: 55.4 (#146)

| Benchmark | Mistral Small | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1338 | 1367 |
| LMArena Creative Writing | 1305 | 1339 |
| LMArena Multi-Turn | 1344 | 1364 |
| LiveBench Language | 30.5% | 56.3% |
| Short-Story Creative Writing | — | 72.9% |

## FAQ

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

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 33.4 on the Noometry Index.

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

Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 34.0 in the Noometry coding category.

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

24 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen2.5-Max has 27.