# Mistral vs Qwen3 235B-A22B

> Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-vs-qwen3-235b-a22b
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Mistral scores higher in 1 category and Qwen3 235B-A22B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.5 to 16.3.
- The biggest single-benchmark swing is Omni-MATH: 7.2% for Mistral and 71.8% for Qwen3 235B-A22B.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral | Qwen3 235B-A22B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 29.4 | 43.2 |
| Rank | 297 | 83 |
| Context | — | 131K |
| Input $/M | — | $0.70 |
| Output $/M | — | $2.80 |
| Weights | Proprietary | Open |

## Coding

- Mistral: 33.2 (#249)
- Qwen3 235B-A22B: 43.8 (#72)

| Benchmark | Mistral | Qwen3 235B-A22B |
|---|---|---|
| LMArena Coding | 1162 | 1445 |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |

## Agentic & Tool Use

- Mistral: —
- Qwen3 235B-A22B: 33.7 (#48)

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

## Reasoning

- Mistral: 21.3 (#199)
- Qwen3 235B-A22B: 15.8 (#302)

| Benchmark | Mistral | Qwen3 235B-A22B |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1433 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| Epoch Capabilities Index | — | 143.87 |
| ForecastBench | — | 59.7 |

## Math

- Mistral: 20.5 (#275)
- Qwen3 235B-A22B: 48.5 (#51)

| Benchmark | Mistral | Qwen3 235B-A22B |
|---|---|---|
| Omni-MATH | 7.2% | 71.8% |
| LMArena Math | 1180 | 1431 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Mistral: 16.3 (#283)
- Qwen3 235B-A22B: 49.5 (#67)

| Benchmark | Mistral | Qwen3 235B-A22B |
|---|---|---|
| MMLU-Pro | 27.7% | 84.4% |
| GPQA (HELM) | 30.3% | 72.7% |
| LMArena Expert | 1125 | 1460 |
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |

## Multilingual

- Mistral: 33.0 (#249)
- Qwen3 235B-A22B: 52.5 (#84)

| Benchmark | Mistral | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1129 | 1410 |
| LMArena Chinese | 1109 | 1481 |
| LMArena French | 1179 | 1445 |
| LMArena German | 1155 | 1432 |
| LMArena Japanese | 1012 | 1400 |
| LMArena Korean | 1032 | 1391 |
| LMArena Russian | 1168 | 1411 |
| LMArena Spanish | 1143 | 1429 |

## Instruction Following

- Mistral: 52.9 (#283)
- Qwen3 235B-A22B: 72.8 (#132)

| Benchmark | Mistral | Qwen3 235B-A22B |
|---|---|---|
| IFEval | 56.8% | 83.5% |
| LMArena Instruction Following | 1152 | 1408 |

## Long Context

- Mistral: 35.0 (#240)
- Qwen3 235B-A22B: 46.1 (#25)

| Benchmark | Mistral | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1154 | 1426 |
| Fiction.LiveBench | — | 75% |

## Writing & Preference

- Mistral: 37.2 (#255)
- Qwen3 235B-A22B: 59.8 (#103)

| Benchmark | Mistral | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1165 | 1419 |
| LMArena Creative Writing | 1158 | 1384 |
| WildBench | 66% | 86.6% |
| LMArena Multi-Turn | 1147 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |

## FAQ

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

Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 29.4 on the Noometry Index.

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

Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 33.2 in the Noometry coding category.

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

22 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Qwen3 235B-A22B has 49.