# Mixtral 8x7B vs Qwen3.7 Plus

> Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 26.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mixtral-8x7b-vs-qwen3-7-plus
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Mixtral 8x7B scores higher in 0 categories and Qwen3.7 Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 11.0.
- The biggest single-benchmark swing is GPQA Diamond: 30.6% for Mixtral 8x7B and 87.9% for Qwen3.7 Plus.
- Both cost about the same: $0.70 input and $0.70 output per million tokens.
- Qwen3.7 Plus accepts more context: 1M tokens versus 32K.
- Mixtral 8x7B has downloadable open weights; the other is API-only.

## Snapshot

| | Mixtral 8x7B | Qwen3.7 Plus |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 26.8 | 45.0 |
| Rank | 328 | 66 |
| Context | 32K | 1M |
| Input $/M | $0.70 | $0.40 |
| Output $/M | $0.70 | $1.60 |
| Weights | Open | Proprietary |

## Coding

- Mixtral 8x7B: 32.2 (#265)
- Qwen3.7 Plus: 36.1 (#200)

| Benchmark | Mixtral 8x7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1127 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |

## Agentic & Tool Use

- Mixtral 8x7B: —
- Qwen3.7 Plus: 21.2 (#130)

| Benchmark | Mixtral 8x7B | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |

## Reasoning

- Mixtral 8x7B: 17.4 (#283)
- Qwen3.7 Plus: 38.4 (#54)

| Benchmark | Mixtral 8x7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1460 |
| DTBench | 49.6% | 84% |
| Epoch Capabilities Index | 118.38 | 147.39 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| LMCA | — | 37.6% |
| Adversarial NLI | 55.2% | — |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |

## Math

- Mixtral 8x7B: 17.2 (#284)
- Qwen3.7 Plus: 49.3 (#47)

| Benchmark | Mixtral 8x7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1147 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| Omni-MATH | 10.5% | — |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |

## Knowledge

- Mixtral 8x7B: 11.0 (#296)
- Qwen3.7 Plus: 54.9 (#46)

| Benchmark | Mixtral 8x7B | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 30.6% | 87.9% |
| LMArena Expert | 1088 | 1467 |
| MMLU-Pro | 33.5% | — |
| GPQA (HELM) | 29.6% | — |
| ARC (AI2) Challenge | 87.3% | — |
| MMLU | 70.6% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |

## Multimodal

- Mixtral 8x7B: —
- Qwen3.7 Plus: 41.2 (#30)

| Benchmark | Mixtral 8x7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1281 |
| LMArena Document | — | 1444 |

## Multilingual

- Mixtral 8x7B: 29.8 (#261)
- Qwen3.7 Plus: 55.0 (#36)

| Benchmark | Mixtral 8x7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1077 | 1445 |
| LMArena Chinese | 1055 | 1510 |
| LMArena French | 1165 | 1471 |
| LMArena German | 1114 | 1471 |
| LMArena Japanese | 931 | 1411 |
| LMArena Korean | 968 | 1416 |
| LMArena Russian | 1090 | 1457 |
| LMArena Spanish | 1110 | 1453 |

## Instruction Following

- Mixtral 8x7B: 51.2 (#292)
- Qwen3.7 Plus: 75.9 (#49)

| Benchmark | Mixtral 8x7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1110 | 1439 |
| IFEval | 57.5% | — |

## Long Context

- Mixtral 8x7B: 33.4 (#255)
- Qwen3.7 Plus: 44.5 (#61)

| Benchmark | Mixtral 8x7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1103 | 1454 |

## Writing & Preference

- Mixtral 8x7B: 34.4 (#265)
- Qwen3.7 Plus: 64.5 (#54)

| Benchmark | Mixtral 8x7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1132 | 1454 |
| LMArena Creative Writing | 1109 | 1439 |
| LMArena Multi-Turn | 1115 | 1459 |
| WildBench | 67.3% | — |

## FAQ

### Is Mixtral 8x7B better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 26.8 on the Noometry Index.

### Which is cheaper, Mixtral 8x7B or Qwen3.7 Plus?

Mixtral 8x7B is cheaper. It lists at $0.70 per million input tokens and $0.70 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.

### Is Mixtral 8x7B or Qwen3.7 Plus better for coding?

Qwen3.7 Plus scores higher on coding benchmarks: 36.1 versus 32.2 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.7 Plus does, with 1M tokens against 32K.

### How many benchmarks do Mixtral 8x7B and Qwen3.7 Plus share?

20 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Qwen3.7 Plus has 32.