# Mistral Medium vs Qwen3-Next 80B-A3B Instruct

> Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 42.5 to 36.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-medium-vs-qwen3-next-80b-a3b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Mistral Medium scores higher in 4 categories and Qwen3-Next 80B-A3B Instruct in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-Next 80B-A3B Instruct leads 41.3 to 24.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 50% for Mistral Medium and 66.7% for Qwen3-Next 80B-A3B Instruct.
- Qwen3-Next 80B-A3B Instruct is cheaper at $0.50 / $2 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 131K.

## Snapshot

| | Mistral Medium | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 36.0 | 42.5 |
| Rank | 211 | 100 |
| Context | 262K | 131K |
| Input $/M | $1.50 | $0.50 |
| Output $/M | $7.50 | $2 |
| Weights | Open | Open |

## Coding

- Mistral Medium: 33.8 (#241)
- Qwen3-Next 80B-A3B Instruct: 41.9 (#101)

| Benchmark | Mistral Medium | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1434 | 1441 |
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | 763.98 | — |

## Agentic & Tool Use

- Mistral Medium: 28.1 (#84)
- Qwen3-Next 80B-A3B Instruct: —

| Benchmark | Mistral Medium | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |

## Reasoning

- Mistral Medium: 23.3 (#165)
- Qwen3-Next 80B-A3B Instruct: 30.1 (#79)

| Benchmark | Mistral Medium | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 50% | 66.7% |
| LMArena Hard Prompts | 1426 | 1428 |
| CritPt | 0% | — |
| DTBench | 75.5% | — |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |

## Math

- Mistral Medium: 27.2 (#238)
- Qwen3-Next 80B-A3B Instruct: 36.3 (#118)

| Benchmark | Mistral Medium | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1409 | 1440 |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| Omni-MATH | — | 46.7% |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |

## Knowledge

- Mistral Medium: 24.9 (#260)
- Qwen3-Next 80B-A3B Instruct: 41.3 (#102)

| Benchmark | Mistral Medium | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Vectara Hallucination Rate | 22.7% | 9.3% |
| LMArena Expert | 1408 | 1416 |
| GPQA Diamond | 59.5% | — |
| Humanity's Last Exam | 4.5% | — |
| MMLU-Pro | — | 78.6% |
| GPQA (HELM) | — | 63% |

## Multimodal

- Mistral Medium: 34.6 (#82)
- Qwen3-Next 80B-A3B Instruct: —

| Benchmark | Mistral Medium | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Vision | 1172 | — |

## Multilingual

- Mistral Medium: 52.3 (#86)
- Qwen3-Next 80B-A3B Instruct: 52.3 (#88)

| Benchmark | Mistral Medium | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1408 | 1407 |
| LMArena Chinese | 1448 | 1461 |
| LMArena French | 1460 | 1415 |
| LMArena German | 1433 | 1416 |
| LMArena Japanese | 1378 | 1398 |
| LMArena Korean | 1382 | 1366 |
| LMArena Russian | 1411 | 1403 |
| LMArena Spanish | 1433 | 1436 |

## Instruction Following

- Mistral Medium: 73.9 (#111)
- Qwen3-Next 80B-A3B Instruct: 71.0 (#154)

| Benchmark | Mistral Medium | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1398 | 1388 |
| IFEval | — | 81% |

## Long Context

- Mistral Medium: 42.9 (#108)
- Qwen3-Next 80B-A3B Instruct: 37.0 (#218)

| Benchmark | Mistral Medium | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Longer Query | 1406 | 1403 |
| Fiction.LiveBench | — | 55.6% |

## Writing & Preference

- Mistral Medium: 60.2 (#97)
- Qwen3-Next 80B-A3B Instruct: 58.2 (#116)

| Benchmark | Mistral Medium | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1424 | 1417 |
| LMArena Creative Writing | 1391 | 1333 |
| LMArena Multi-Turn | 1418 | 1415 |
| Short-Story Creative Writing | 77.3% | — |
| WildBench | — | 80.7% |

## FAQ

### Is Mistral Medium better than Qwen3-Next 80B-A3B Instruct?

Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 42.5 to 36.0 on the Noometry Index.

### Which is cheaper, Mistral Medium or Qwen3-Next 80B-A3B Instruct?

Qwen3-Next 80B-A3B Instruct is cheaper. It lists at $0.50 per million input tokens and $2 per million output tokens; Mistral Medium lists at $1.50 and $7.50.

### Is Mistral Medium or Qwen3-Next 80B-A3B Instruct better for coding?

Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 41.9 versus 33.8 in the Noometry coding category.

### Which has the bigger context window?

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

### How many benchmarks do Mistral Medium and Qwen3-Next 80B-A3B Instruct share?

19 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.