# Mistral Small 3.2 vs Qwen3 8B

> Qwen3 8B is the stronger model overall, scoring 33.7 to 31.2 on the Noometry Index. Mistral Small 3.2 costs 2.3× less per token, which makes it the better buy when Qwen3 8B's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-small-3-2-vs-qwen3-8b
- Last updated: 2026-10-12
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Mistral Small 3.2 scores higher in 1 category and Qwen3 8B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 8B leads 36.1 to 26.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 30.3% for Mistral Small 3.2 and 56.1% for Qwen3 8B.
- Mistral Small 3.2 is cheaper at $0.0938 / $0.25 per million input/output tokens, against $0.18 / $0.70 for Qwen3 8B.
- Mistral Small 3.2 accepts more context: 256K tokens versus 131K.

## Snapshot

| | Mistral Small 3.2 | Qwen3 8B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.2 | 33.7 |
| Rank | 280 | 238 |
| Context | 256K | 131K |
| Input $/M | $0.0938 | $0.18 |
| Output $/M | $0.25 | $0.70 |
| Weights | Open | Open |

## Coding

- Mistral Small 3.2: —
- Qwen3 8B: 34.0 (#248)

| Benchmark | Mistral Small 3.2 | Qwen3 8B |
|---|---|---|
| SciCode | — | 22.6% |

## Agentic & Tool Use

- Mistral Small 3.2: —
- Qwen3 8B: 30.2 (#78)

| Benchmark | Mistral Small 3.2 | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |

## Reasoning

- Mistral Small 3.2: 18.1 (#287)
- Qwen3 8B: 16.6 (#303)

| Benchmark | Mistral Small 3.2 | Qwen3 8B |
|---|---|---|
| Chess Puzzles | 1% | 5% |
| Epoch Capabilities Index | 131.74 | 136.17 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | — | 0% |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |

## Math

- Mistral Small 3.2: 26.3 (#260)
- Qwen3 8B: 34.9 (#191)

| Benchmark | Mistral Small 3.2 | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30.3% | 56.1% |

## Knowledge

- Mistral Small 3.2: 26.7 (#256)
- Qwen3 8B: 36.1 (#173)

| Benchmark | Mistral Small 3.2 | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 49.1% | 56.8% |
| Vectara Hallucination Rate | — | 4.8% |

## Long Context

- Mistral Small 3.2: —
- Qwen3 8B: 37.9 (#210)

| Benchmark | Mistral Small 3.2 | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |

## Writing & Preference

- Mistral Small 3.2: 45.0 (#224)
- Qwen3 8B: —

| Benchmark | Mistral Small 3.2 | Qwen3 8B |
|---|---|---|
| EQ-Bench Creative Writing | 1255 | — |

## FAQ

### Is Mistral Small 3.2 better than Qwen3 8B?

Qwen3 8B is the stronger model overall, scoring 33.7 to 31.2 on the Noometry Index. Mistral Small 3.2 costs 2.3× less per token, which makes it the better buy when Qwen3 8B's lead doesn't matter for your workload.

### Which is cheaper, Mistral Small 3.2 or Qwen3 8B?

Mistral Small 3.2 is cheaper. It lists at $0.0938 per million input tokens and $0.25 per million output tokens; Qwen3 8B lists at $0.18 and $0.70.

### Which has the bigger context window?

Mistral Small 3.2 does, with 256K tokens against 131K.

### How many benchmarks do Mistral Small 3.2 and Qwen3 8B share?

4 benchmarks have published results for both models. Mistral Small 3.2 has 6 scored results on Noometry and Qwen3 8B has 11.