# Mistral Small 3 vs Qwen Max

> Qwen Max is the stronger model overall, scoring 34.4 to 30.9 on the Noometry Index. Mistral Small 3 costs 49× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-small-3-vs-qwen-max
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Mistral Small 3 scores higher in 1 category and Qwen Max in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Max leads 48.0 to 32.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for Mistral Small 3 and 16.1% for Qwen Max.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Mistral Small 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Small 3 | Qwen Max |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.9 | 34.4 |
| Rank | 268 | 226 |
| Context | 33K | 33K |
| Input $/M | $0.05 | $1.60 |
| Output $/M | $0.08 | $6.40 |
| Weights | Open | Proprietary |

## Coding

- Mistral Small 3: 36.0 (#203)
- Qwen Max: 30.3 (#288)

| Benchmark | Mistral Small 3 | Qwen Max |
|---|---|---|
| LMArena Coding | 1246 | 1288 |
| Aider Polyglot | — | 21.8% |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |

## Reasoning

- Mistral Small 3: 18.2 (#269)
- Qwen Max: 24.1 (#154)

| Benchmark | Mistral Small 3 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1270 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 127.06 | — |

## Math

- Mistral Small 3: 15.3 (#290)
- Qwen Max: 21.0 (#272)

| Benchmark | Mistral Small 3 | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 16.1% |
| LMArena Math | 1240 | 1275 |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |

## Knowledge

- Mistral Small 3: 25.0 (#258)
- Qwen Max: 30.3 (#222)

| Benchmark | Mistral Small 3 | Qwen Max |
|---|---|---|
| GPQA Diamond | 47.3% | 56.1% |
| LMArena Expert | 1202 | 1248 |
| Confabulations | 25.2% | — |

## Multilingual

- Mistral Small 3: 37.5 (#231)
- Qwen Max: 42.0 (#197)

| Benchmark | Mistral Small 3 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1198 | 1263 |
| LMArena Chinese | 1204 | 1254 |
| LMArena French | 1202 | 1329 |
| LMArena German | 1211 | 1254 |
| LMArena Japanese | 1111 | 1205 |
| LMArena Korean | 1188 | 1141 |
| LMArena Russian | 1216 | 1274 |
| LMArena Spanish | — | 1290 |

## Instruction Following

- Mistral Small 3: 63.9 (#224)
- Qwen Max: 66.7 (#203)

| Benchmark | Mistral Small 3 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1214 | 1262 |

## Long Context

- Mistral Small 3: 37.8 (#206)
- Qwen Max: 39.4 (#175)

| Benchmark | Mistral Small 3 | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1246 | 1289 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Mistral Small 3: 32.4 (#275)
- Qwen Max: 48.0 (#200)

| Benchmark | Mistral Small 3 | Qwen Max |
|---|---|---|
| LMArena Text | 1234 | 1282 |
| LMArena Creative Writing | 1195 | 1248 |
| LMArena Multi-Turn | 1217 | 1277 |
| EQ-Bench Creative Writing | 707 | — |

## FAQ

### Is Mistral Small 3 better than Qwen Max?

Qwen Max is the stronger model overall, scoring 34.4 to 30.9 on the Noometry Index. Mistral Small 3 costs 49× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.

### Which is cheaper, Mistral Small 3 or Qwen Max?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen Max lists at $1.60 and $6.40.

### Is Mistral Small 3 or Qwen Max better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 30.3 in the Noometry coding category.

### Which has the bigger context window?

Both accept 33K tokens.

### How many benchmarks do Mistral Small 3 and Qwen Max share?

18 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen Max has 23.