# Mistral Small vs Qwen3 235B-A22B

> Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 33.1 on the Noometry Index. Mistral Small costs 4.7× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-small-vs-qwen3-235b-a22b
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Mistral Small scores higher in 1 category and Qwen3 235B-A22B in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 48.5 to 15.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 5.8% for Mistral Small and 86.7% for Qwen3 235B-A22B.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- Mistral Small accepts more context: 256K tokens versus 131K.

## Snapshot

| | Mistral Small | Qwen3 235B-A22B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.1 | 43.2 |
| Rank | 238 | 83 |
| Context | 256K | 131K |
| Input $/M | $0.15 | $0.70 |
| Output $/M | $0.60 | $2.80 |
| Weights | Open | Open |

## Coding

- Mistral Small: 33.5 (#242)
- Qwen3 235B-A22B: 43.8 (#72)

| Benchmark | Mistral Small | Qwen3 235B-A22B |
|---|---|---|
| SciCode | 26.5% | 42.4% |
| LMArena Coding | 1363 | 1445 |
| Aider Polyglot | — | 59.6% |
| WeirdML | — | 41% |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |

## Agentic & Tool Use

- Mistral Small: 27.9 (#87)
- Qwen3 235B-A22B: 33.7 (#48)

| Benchmark | Mistral Small | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | 52.1% |
| Vending-Bench 2 | — | -11.34 |

## Reasoning

- Mistral Small: 19.3 (#238)
- Qwen3 235B-A22B: 15.8 (#302)

| Benchmark | Mistral Small | Qwen3 235B-A22B |
|---|---|---|
| Kagi LLM Benchmark | 37.8% | 69.4% |
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1336 | 1433 |
| DTBench | 70.9% | 80.3% |
| LMCA | 20.6% | 29.3% |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| ARC-AGI-1 | — | 11% |
| Chess Puzzles | — | 12% |
| LiveBench Reasoning | 44.8% | — |
| Mystery Game Puzzles | — | 9% |
| LiveBench Data Analysis | 53.7% | — |
| Epoch Capabilities Index | — | 143.87 |
| ForecastBench | — | 59.7 |
| LiveBench | 44% | — |

## Math

- Mistral Small: 15.4 (#287)
- Qwen3 235B-A22B: 48.5 (#51)

| Benchmark | Mistral Small | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 86.7% |
| LMArena Math | 1341 | 1431 |
| MATH Level 5 | 46.8% | 68.9% |
| Omni-MATH | — | 71.8% |
| LiveBench Math | 39.9% | — |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Mistral Small: 30.9 (#214)
- Qwen3 235B-A22B: 49.5 (#67)

| Benchmark | Mistral Small | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 47.5% | 80.1% |
| Vectara Hallucination Rate | 5.1% | 9.3% |
| LMArena Expert | 1293 | 1460 |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| GPQA (HELM) | — | 72.7% |
| MMLU | 68.7% | — |

## Multimodal

- Mistral Small: 32.9 (#91)
- Qwen3 235B-A22B: —

| Benchmark | Mistral Small | Qwen3 235B-A22B |
|---|---|---|
| LMArena Vision | 1142 | — |

## Multilingual

- Mistral Small: 45.7 (#164)
- Qwen3 235B-A22B: 52.5 (#84)

| Benchmark | Mistral Small | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1315 | 1410 |
| LMArena Chinese | 1342 | 1481 |
| LMArena French | 1337 | 1445 |
| LMArena German | 1341 | 1432 |
| LMArena Japanese | 1275 | 1400 |
| LMArena Korean | 1260 | 1391 |
| LMArena Russian | 1324 | 1411 |
| LMArena Spanish | 1346 | 1429 |

## Instruction Following

- Mistral Small: 66.6 (#204)
- Qwen3 235B-A22B: 72.8 (#132)

| Benchmark | Mistral Small | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1310 | 1408 |
| LiveBench Instruction Following | 63.7% | — |
| IFEval | — | 83.5% |

## Long Context

- Mistral Small: 40.4 (#151)
- Qwen3 235B-A22B: 46.1 (#25)

| Benchmark | Mistral Small | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1327 | 1426 |
| Fiction.LiveBench | — | 75% |

## Writing & Preference

- Mistral Small: 52.6 (#165)
- Qwen3 235B-A22B: 59.8 (#103)

| Benchmark | Mistral Small | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1338 | 1419 |
| LMArena Creative Writing | 1304 | 1384 |
| LMArena Multi-Turn | 1344 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
| WildBench | — | 86.6% |
| LiveBench Language | 30.5% | — |

## FAQ

### Is Mistral Small better than Qwen3 235B-A22B?

Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 33.1 on the Noometry Index. Mistral Small costs 4.7× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.

### Which is cheaper, Mistral Small or Qwen3 235B-A22B?

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.

### Is Mistral Small or Qwen3 235B-A22B better for coding?

Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

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

### How many benchmarks do Mistral Small and Qwen3 235B-A22B share?

27 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen3 235B-A22B has 49.