# Mistral Small 3 vs Qwen3 32B

> Qwen3 32B is the stronger model overall, scoring 38.8 to 30.9 on the Noometry Index. Mistral Small 3 costs 21× less per token, which makes it the better buy when Qwen3 32B's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-small-3-vs-qwen3-32b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and Qwen3 32B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 32B leads 37.9 to 15.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for Mistral Small 3 and 66.9% for Qwen3 32B.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
- Qwen3 32B accepts more context: 131K tokens versus 33K.

## Snapshot

| | Mistral Small 3 | Qwen3 32B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.9 | 38.8 |
| Rank | 268 | 166 |
| Context | 33K | 131K |
| Input $/M | $0.05 | $0.70 |
| Output $/M | $0.08 | $2.80 |
| Weights | Open | Open |

## Coding

- Mistral Small 3: 36.0 (#203)
- Qwen3 32B: 37.3 (#184)

| Benchmark | Mistral Small 3 | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1246 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |

## Agentic & Tool Use

- Mistral Small 3: —
- Qwen3 32B: 32.3 (#58)

| Benchmark | Mistral Small 3 | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |

## Reasoning

- Mistral Small 3: 18.2 (#269)
- Qwen3 32B: 19.6 (#233)

| Benchmark | Mistral Small 3 | Qwen3 32B |
|---|---|---|
| Chess Puzzles | 0% | 5% |
| LMArena Hard Prompts | 1233 | 1335 |
| Epoch Capabilities Index | 127.06 | 138.51 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |

## Math

- Mistral Small 3: 15.3 (#290)
- Qwen3 32B: 37.9 (#89)

| Benchmark | Mistral Small 3 | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 66.9% |
| LMArena Math | 1240 | 1399 |

## Knowledge

- Mistral Small 3: 25.0 (#258)
- Qwen3 32B: 40.0 (#112)

| Benchmark | Mistral Small 3 | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 47.3% | 65.7% |
| LMArena Expert | 1202 | 1362 |
| Confabulations | 25.2% | — |
| Vectara Hallucination Rate | — | 5.9% |

## Multilingual

- Mistral Small 3: 37.5 (#231)
- Qwen3 32B: 45.8 (#162)

| Benchmark | Mistral Small 3 | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1198 | 1317 |
| LMArena Chinese | 1204 | 1357 |
| LMArena German | 1211 | 1341 |
| LMArena Russian | 1216 | 1311 |
| LMArena French | 1202 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1188 | — |

## Instruction Following

- Mistral Small 3: 63.9 (#224)
- Qwen3 32B: 69.1 (#174)

| Benchmark | Mistral Small 3 | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1214 | 1305 |

## Long Context

- Mistral Small 3: 37.8 (#206)
- Qwen3 32B: 43.7 (#83)

| Benchmark | Mistral Small 3 | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1246 | 1327 |
| Fiction.LiveBench | — | 74.2% |

## Writing & Preference

- Mistral Small 3: 32.4 (#275)
- Qwen3 32B: 53.1 (#158)

| Benchmark | Mistral Small 3 | Qwen3 32B |
|---|---|---|
| LMArena Text | 1234 | 1340 |
| LMArena Creative Writing | 1195 | 1297 |
| LMArena Multi-Turn | 1217 | 1331 |
| EQ-Bench Creative Writing | 707 | — |

## FAQ

### Is Mistral Small 3 better than Qwen3 32B?

Qwen3 32B is the stronger model overall, scoring 38.8 to 30.9 on the Noometry Index. Mistral Small 3 costs 21× less per token, which makes it the better buy when Qwen3 32B's lead doesn't matter for your workload.

### Which is cheaper, Mistral Small 3 or Qwen3 32B?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.

### Is Mistral Small 3 or Qwen3 32B better for coding?

Qwen3 32B scores higher on coding benchmarks: 37.3 versus 36.0 in the Noometry coding category.

### Which has the bigger context window?

Qwen3 32B does, with 131K tokens against 33K.

### How many benchmarks do Mistral Small 3 and Qwen3 32B share?

17 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen3 32B has 26.