# Mistral Medium 3.5 vs Qwen2.5 7B Instruct

> Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 28.6 on the Noometry Index. Qwen2.5 7B Instruct costs 9.8× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-medium-3-5-vs-qwen2-5-7b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Mistral Medium 3.5 scores higher in 5 categories and Qwen2.5 7B Instruct in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Medium 3.5 leads 36.4 to 11.8.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 131K.

## Snapshot

| | Mistral Medium 3.5 | Qwen2.5 7B Instruct |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 39.6 | 28.6 |
| Rank | 151 | 314 |
| Context | 262K | 131K |
| Input $/M | $1.50 | $0.17 |
| Output $/M | $7.50 | $0.70 |
| Weights | Open | Open |

## Coding

- Mistral Medium 3.5: 35.7 (#208)
- Qwen2.5 7B Instruct: 35.9 (#204)

| Benchmark | Mistral Medium 3.5 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena WebDev | 1263 | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1461 | — |
| BigCodeBench Complete | — | 46.1% |

## Agentic & Tool Use

- Mistral Medium 3.5: —
- Qwen2.5 7B Instruct: 23.5 (#117)

| Benchmark | Mistral Medium 3.5 | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |

## Reasoning

- Mistral Medium 3.5: 16.6 (#290)
- Qwen2.5 7B Instruct: 14.3 (#317)

| Benchmark | Mistral Medium 3.5 | Qwen2.5 7B Instruct |
|---|---|---|
| Epoch Capabilities Index | 141.42 | 118.44 |
| Kagi LLM Benchmark | 41.4% | — |
| NYT Connections (extended) | 12.9% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1436 | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |

## Math

- Mistral Medium 3.5: 36.4 (#113)
- Qwen2.5 7B Instruct: 11.8 (#300)

| Benchmark | Mistral Medium 3.5 | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1432 | — |

## Knowledge

- Mistral Medium 3.5: 39.3 (#123)
- Qwen2.5 7B Instruct: 17.0 (#281)

| Benchmark | Mistral Medium 3.5 | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1431 | — |
| MMLU | — | 72.9% |

## Multimodal

- Mistral Medium 3.5: 37.6 (#64)
- Qwen2.5 7B Instruct: —

| Benchmark | Mistral Medium 3.5 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Vision | 1222 | — |

## Multilingual

- Mistral Medium 3.5: 52.1 (#93)
- Qwen2.5 7B Instruct: —

| Benchmark | Mistral Medium 3.5 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1405 | — |
| LMArena Chinese | 1443 | — |
| LMArena French | 1448 | — |
| LMArena German | 1453 | — |
| LMArena Korean | 1387 | — |
| LMArena Russian | 1396 | — |
| LMArena Spanish | 1406 | — |

## Instruction Following

- Mistral Medium 3.5: 74.7 (#87)
- Qwen2.5 7B Instruct: 63.4 (#226)

| Benchmark | Mistral Medium 3.5 | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1414 | — |

## Long Context

- Mistral Medium 3.5: 43.2 (#101)
- Qwen2.5 7B Instruct: —

| Benchmark | Mistral Medium 3.5 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1414 | — |

## Writing & Preference

- Mistral Medium 3.5: 58.6 (#113)
- Qwen2.5 7B Instruct: 48.8 (#194)

| Benchmark | Mistral Medium 3.5 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1421 | — |
| LMArena Creative Writing | 1372 | — |
| WildBench | — | 73.1% |
| EQ-Bench 4 | 993 | — |
| LMArena Multi-Turn | 1423 | — |

## FAQ

### Is Mistral Medium 3.5 better than Qwen2.5 7B Instruct?

Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 28.6 on the Noometry Index. Qwen2.5 7B Instruct costs 9.8× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

### Which is cheaper, Mistral Medium 3.5 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; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is Mistral Medium 3.5 or Qwen2.5 7B Instruct better for coding?

They score almost the same on coding (35.7 vs 35.9); test both on your own repository before choosing.

### Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 131K.

### How many benchmarks do Mistral Medium 3.5 and Qwen2.5 7B Instruct share?

1 benchmark has published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Qwen2.5 7B Instruct has 15.