# Mistral Large vs Qwen2.5 32B Instruct

> Mistral Large is the stronger model overall, scoring 31.6 to 29.7 on the Noometry Index. Qwen2.5 32B Instruct costs 2.4× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-large-vs-qwen2-5-32b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Mistral Large scores higher in 2 categories and Qwen2.5 32B Instruct in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Large leads 30.0 to 24.9.
- The biggest single-benchmark swing is BigCodeBench Instruct: 30% for Mistral Large and 45% for Qwen2.5 32B Instruct.
- Qwen2.5 32B Instruct is cheaper at $0.70 / $2.80 per million input/output tokens, against $2 / $6 for Mistral Large.

## Snapshot

| | Mistral Large | Qwen2.5 32B Instruct |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.6 | 29.7 |
| Rank | 258 | 291 |
| Context | 131K | 131K |
| Input $/M | $2 | $0.70 |
| Output $/M | $6 | $2.80 |
| Weights | Open | Open |

## Coding

- Mistral Large: 33.8 (#240)
- Qwen2.5 32B Instruct: 38.1 (#165)

| Benchmark | Mistral Large | Qwen2.5 32B Instruct |
|---|---|---|
| BigCodeBench Instruct | 30% | 45% |
| BigCodeBench Complete | 38.3% | 52.3% |
| SciCode | 36.2% | — |
| LiveBench Coding | 47.1% | — |
| LMArena Coding | 1277 | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |

## Agentic & Tool Use

- Mistral Large: 28.4 (#83)
- Qwen2.5 32B Instruct: —

| Benchmark | Mistral Large | Qwen2.5 32B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |

## Reasoning

- Mistral Large: 15.4 (#305)
- Qwen2.5 32B Instruct: 18.5 (#262)

| Benchmark | Mistral Large | Qwen2.5 32B Instruct |
|---|---|---|
| Epoch Capabilities Index | 128.52 | 128.52 |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 43.5% | — |
| LMArena Hard Prompts | 1257 | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |

## Math

- Mistral Large: 17.1 (#285)
- Qwen2.5 32B Instruct: 15.3 (#289)

| Benchmark | Mistral Large | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 7.4% |
| MATH Level 5 | 50.3% | 56.1% |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| LMArena Math | 1262 | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |

## Knowledge

- Mistral Large: 30.0 (#224)
- Qwen2.5 32B Instruct: 24.9 (#259)

| Benchmark | Mistral Large | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | 51.3% | 46.1% |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| LMArena Expert | 1232 | — |
| MMLU | 80% | — |

## Multilingual

- Mistral Large: 40.1 (#214)
- Qwen2.5 32B Instruct: —

| Benchmark | Mistral Large | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1237 | — |
| LMArena Chinese | 1240 | — |
| LMArena French | 1324 | — |
| LMArena German | 1254 | — |
| LMArena Japanese | 1187 | — |
| LMArena Korean | 1202 | — |
| LMArena Russian | 1257 | — |
| LMArena Spanish | 1268 | — |

## Instruction Following

- Mistral Large: 68.1 (#186)
- Qwen2.5 32B Instruct: —

| Benchmark | Mistral Large | Qwen2.5 32B Instruct |
|---|---|---|
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
| LMArena Instruction Following | 1249 | — |

## Long Context

- Mistral Large: 38.3 (#194)
- Qwen2.5 32B Instruct: —

| Benchmark | Mistral Large | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Longer Query | 1262 | — |

## Writing & Preference

- Mistral Large: 40.9 (#237)
- Qwen2.5 32B Instruct: —

| Benchmark | Mistral Large | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Text | 1266 | — |
| LMArena Creative Writing | 1243 | — |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LMArena Multi-Turn | 1260 | — |
| LiveBench Language | 39.4% | — |

## FAQ

### Is Mistral Large better than Qwen2.5 32B Instruct?

Mistral Large is the stronger model overall, scoring 31.6 to 29.7 on the Noometry Index. Qwen2.5 32B Instruct costs 2.4× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.

### Which is cheaper, Mistral Large or Qwen2.5 32B Instruct?

Qwen2.5 32B Instruct is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Mistral Large lists at $2 and $6.

### Is Mistral Large or Qwen2.5 32B Instruct better for coding?

Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.1 versus 33.8 in the Noometry coding category.

### Which has the bigger context window?

Both accept 131K tokens.

### How many benchmarks do Mistral Large and Qwen2.5 32B Instruct share?

6 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen2.5 32B Instruct has 7.