# Mixtral 8x7B vs Qwen2.5 7B Instruct

> Qwen2.5 7B Instruct is the stronger model overall, scoring 28.6 to 26.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mixtral-8x7b-vs-qwen2-5-7b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 9

## Summary

- They share 9 benchmarks with published results for both. Mixtral 8x7B scores higher in 2 categories and Qwen2.5 7B Instruct in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 7B Instruct leads 48.8 to 34.4.
- The biggest single-benchmark swing is MMLU-Pro: 33.5% for Mixtral 8x7B and 53.9% for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.70 / $0.70 for Mixtral 8x7B.
- Qwen2.5 7B Instruct accepts more context: 131K tokens versus 32K.

## Snapshot

| | Mixtral 8x7B | Qwen2.5 7B Instruct |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 26.8 | 28.6 |
| Rank | 328 | 314 |
| Context | 32K | 131K |
| Input $/M | $0.70 | $0.17 |
| Output $/M | $0.70 | $0.70 |
| Weights | Open | Open |

## Coding

- Mixtral 8x7B: 32.2 (#265)
- Qwen2.5 7B Instruct: 35.9 (#204)

| Benchmark | Mixtral 8x7B | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1127 | — |
| BigCodeBench Complete | — | 46.1% |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |

## Agentic & Tool Use

- Mixtral 8x7B: —
- Qwen2.5 7B Instruct: 23.5 (#117)

| Benchmark | Mixtral 8x7B | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |

## Reasoning

- Mixtral 8x7B: 17.4 (#283)
- Qwen2.5 7B Instruct: 14.3 (#317)

| Benchmark | Mixtral 8x7B | Qwen2.5 7B Instruct |
|---|---|---|
| DTBench | 49.6% | 47.7% |
| Epoch Capabilities Index | 118.38 | 118.44 |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1115 | — |
| LMCA | — | 6.4% |
| Adversarial NLI | 55.2% | — |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |

## Math

- Mixtral 8x7B: 17.2 (#284)
- Qwen2.5 7B Instruct: 11.8 (#300)

| Benchmark | Mixtral 8x7B | Qwen2.5 7B Instruct |
|---|---|---|
| Omni-MATH | 10.5% | 29.4% |
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| LMArena Math | 1147 | — |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |

## Knowledge

- Mixtral 8x7B: 11.0 (#296)
- Qwen2.5 7B Instruct: 17.0 (#281)

| Benchmark | Mixtral 8x7B | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 30.6% | 35.5% |
| MMLU-Pro | 33.5% | 53.9% |
| GPQA (HELM) | 29.6% | 34.1% |
| MMLU | 70.6% | 72.9% |
| LMArena Expert | 1088 | — |
| ARC (AI2) Challenge | 87.3% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |

## Multilingual

- Mixtral 8x7B: 29.8 (#261)
- Qwen2.5 7B Instruct: —

| Benchmark | Mixtral 8x7B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1077 | — |
| LMArena Chinese | 1055 | — |
| LMArena French | 1165 | — |
| LMArena German | 1114 | — |
| LMArena Japanese | 931 | — |
| LMArena Korean | 968 | — |
| LMArena Russian | 1090 | — |
| LMArena Spanish | 1110 | — |

## Instruction Following

- Mixtral 8x7B: 51.2 (#292)
- Qwen2.5 7B Instruct: 63.4 (#226)

| Benchmark | Mixtral 8x7B | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | 57.5% | 74.1% |
| LMArena Instruction Following | 1110 | — |

## Long Context

- Mixtral 8x7B: 33.4 (#255)
- Qwen2.5 7B Instruct: —

| Benchmark | Mixtral 8x7B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1103 | — |

## Writing & Preference

- Mixtral 8x7B: 34.4 (#265)
- Qwen2.5 7B Instruct: 48.8 (#194)

| Benchmark | Mixtral 8x7B | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | 67.3% | 73.1% |
| LMArena Text | 1132 | — |
| LMArena Creative Writing | 1109 | — |
| LMArena Multi-Turn | 1115 | — |

## FAQ

### Is Mixtral 8x7B better than Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is the stronger model overall, scoring 28.6 to 26.8 on the Noometry Index.

### Which is cheaper, Mixtral 8x7B or Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Mixtral 8x7B lists at $0.70 and $0.70.

### Is Mixtral 8x7B or Qwen2.5 7B Instruct better for coding?

Qwen2.5 7B Instruct scores higher on coding benchmarks: 35.9 versus 32.2 in the Noometry coding category.

### Which has the bigger context window?

Qwen2.5 7B Instruct does, with 131K tokens against 32K.

### How many benchmarks do Mixtral 8x7B and Qwen2.5 7B Instruct share?

9 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Qwen2.5 7B Instruct has 15.