# Mixtral 8x22B vs Qwen Plus

> Qwen Plus is the stronger model overall, scoring 37.1 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mixtral-8x22b-vs-qwen-plus
- Last updated: 2026-10-12
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Mixtral 8x22B scores higher in 0 categories and Qwen Plus in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Plus leads 52.2 to 36.9.
- The biggest single-benchmark swing is MATH Level 5: 24.2% for Mixtral 8x22B and 65.3% for Qwen Plus.
- Qwen Plus is cheaper at $0.40 / $1.20 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Qwen Plus accepts more context: 1M tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.

## Snapshot

| | Mixtral 8x22B | Qwen Plus |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 27.1 | 37.1 |
| Rank | 333 | 210 |
| Context | 64K | 1M |
| Input $/M | $2 | $0.40 |
| Output $/M | $6 | $1.20 |
| Weights | Open | Proprietary |

## Coding

- Mixtral 8x22B: 24.2 (#329)
- Qwen Plus: 38.9 (#167)

| Benchmark | Mixtral 8x22B | Qwen Plus |
|---|---|---|
| LMArena Coding | 1166 | 1328 |
| WeirdML | 3.2% | — |
| BigCodeBench Instruct | 40.6% | — |
| BigCodeBench Complete | 50.2% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |

## Agentic & Tool Use

- Mixtral 8x22B: 23.1 (#127)
- Qwen Plus: —

| Benchmark | Mixtral 8x22B | Qwen Plus |
|---|---|---|
| Cybench | 7.5% | — |

## Reasoning

- Mixtral 8x22B: 19.9 (#248)
- Qwen Plus: 28.4 (#107)

| Benchmark | Mixtral 8x22B | Qwen Plus |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1317 |
| DTBench | 55.1% | 81.1% |
| Kagi LLM Benchmark | — | 63.3% |
| LMCA | — | 24% |
| Epoch Capabilities Index | 122.03 | — |
| ForecastBench | 56.3 | — |

## Math

- Mixtral 8x22B: 22.9 (#275)
- Qwen Plus: 23.3 (#271)

| Benchmark | Mixtral 8x22B | Qwen Plus |
|---|---|---|
| LMArena Math | 1184 | 1326 |
| MATH Level 5 | 24.2% | 65.3% |
| OTIS Mock AIME 2024-2025 | — | 17.8% |
| Omni-MATH | 16.3% | — |
| FrontierMath (Feb 2025 set) | — | 1.7% |

## Knowledge

- Mixtral 8x22B: 15.1 (#293)
- Qwen Plus: 27.4 (#251)

| Benchmark | Mixtral 8x22B | Qwen Plus |
|---|---|---|
| GPQA Diamond | 34.1% | 48.1% |
| LMArena Expert | 1113 | 1328 |
| MMLU-Pro | 46% | — |
| GPQA (HELM) | 33.4% | — |
| MMLU | 77.8% | — |

## Multilingual

- Mixtral 8x22B: 32.8 (#255)
- Qwen Plus: 45.1 (#175)

| Benchmark | Mixtral 8x22B | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1128 | 1310 |
| LMArena Chinese | 1116 | 1347 |
| LMArena Japanese | 1037 | 1251 |
| LMArena Russian | 1158 | 1323 |
| LMArena French | 1166 | — |
| LMArena German | 1141 | — |
| LMArena Korean | 1057 | — |
| LMArena Spanish | 1151 | — |

## Instruction Following

- Mixtral 8x22B: 57.7 (#266)
- Qwen Plus: 68.8 (#181)

| Benchmark | Mixtral 8x22B | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1147 | 1303 |
| IFEval | 72.4% | — |

## Long Context

- Mixtral 8x22B: 34.7 (#247)
- Qwen Plus: 40.3 (#158)

| Benchmark | Mixtral 8x22B | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1144 | 1324 |

## Writing & Preference

- Mixtral 8x22B: 36.9 (#262)
- Qwen Plus: 52.2 (#176)

| Benchmark | Mixtral 8x22B | Qwen Plus |
|---|---|---|
| LMArena Text | 1162 | 1326 |
| LMArena Creative Writing | 1141 | 1293 |
| LMArena Multi-Turn | 1130 | 1336 |
| WildBench | 71.1% | — |

## FAQ

### Is Mixtral 8x22B better than Qwen Plus?

Qwen Plus is the stronger model overall, scoring 37.1 to 27.1 on the Noometry Index.

### Which is cheaper, Mixtral 8x22B or Qwen Plus?

Qwen Plus is cheaper. It lists at $0.40 per million input tokens and $1.20 per million output tokens; Mixtral 8x22B lists at $2 and $6.

### Is Mixtral 8x22B or Qwen Plus better for coding?

Qwen Plus scores higher on coding benchmarks: 38.9 versus 24.2 in the Noometry coding category.

### Which has the bigger context window?

Qwen Plus does, with 1M tokens against 64K.

### How many benchmarks do Mixtral 8x22B and Qwen Plus share?

16 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Qwen Plus has 20.