# Mistral Large 3 vs Qwen2.5 72B Instruct

> Mistral Large 3 is the stronger model overall, scoring 38.6 to 31.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-large-3-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Mistral Large 3 scores higher in 7 categories and Qwen2.5 72B Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 3 leads 36.0 to 18.1.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Mistral Large 3 accepts more context: 262K tokens versus 131K.

## Snapshot

| | Mistral Large 3 | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 38.6 | 31.5 |
| Rank | 172 | 259 |
| Context | 262K | 131K |
| Input $/M | $0.25 | $1.40 |
| Output $/M | $0.75 | $5.60 |
| Weights | Open | Open |

## Coding

- Mistral Large 3: 34.1 (#230)
- Qwen2.5 72B Instruct: 32.8 (#256)

| Benchmark | Mistral Large 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1447 | 1293 |
| LMArena WebDev | 1230 | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- Mistral Large 3: —
- Qwen2.5 72B Instruct: 22.0 (#124)

| Benchmark | Mistral Large 3 | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Mistral Large 3: 14.6 (#314)
- Qwen2.5 72B Instruct: 21.4 (#197)

| Benchmark | Mistral Large 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1271 |
| Kagi LLM Benchmark | 50.9% | — |
| NYT Connections (extended) | 7.5% | — |
| Thematic Generalization | 23% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129.01 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Mistral Large 3: 36.0 (#131)
- Qwen2.5 72B Instruct: 18.1 (#281)

| Benchmark | Mistral Large 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1415 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |

## Knowledge

- Mistral Large 3: 35.5 (#173)
- Qwen2.5 72B Instruct: 26.9 (#247)

| Benchmark | Mistral Large 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1421 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 14.5% | — |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multimodal

- Mistral Large 3: 37.6 (#65)
- Qwen2.5 72B Instruct: —

| Benchmark | Mistral Large 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1222 | — |

## Multilingual

- Mistral Large 3: 52.6 (#79)
- Qwen2.5 72B Instruct: 41.2 (#208)

| Benchmark | Mistral Large 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1412 | 1252 |
| LMArena Chinese | 1448 | 1272 |
| LMArena French | 1456 | 1279 |
| LMArena German | 1438 | 1234 |
| LMArena Japanese | 1399 | 1180 |
| LMArena Korean | 1384 | 1188 |
| LMArena Russian | 1412 | 1264 |
| LMArena Spanish | 1437 | 1255 |

## Instruction Following

- Mistral Large 3: 74.1 (#104)
- Qwen2.5 72B Instruct: 65.7 (#216)

| Benchmark | Mistral Large 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1402 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Mistral Large 3: 43.1 (#102)
- Qwen2.5 72B Instruct: 38.9 (#183)

| Benchmark | Mistral Large 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1413 | 1282 |

## Writing & Preference

- Mistral Large 3: 60.2 (#100)
- Qwen2.5 72B Instruct: 46.9 (#210)

| Benchmark | Mistral Large 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1427 | 1269 |
| LMArena Creative Writing | 1385 | 1221 |
| LMArena Multi-Turn | 1429 | 1272 |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | — | 80.2% |

## FAQ

### Is Mistral Large 3 better than Qwen2.5 72B Instruct?

Mistral Large 3 is the stronger model overall, scoring 38.6 to 31.5 on the Noometry Index.

### Which is cheaper, Mistral Large 3 or Qwen2.5 72B Instruct?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

### Is Mistral Large 3 or Qwen2.5 72B Instruct better for coding?

Mistral Large 3 scores higher on coding benchmarks: 34.1 versus 32.8 in the Noometry coding category.

### Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 131K.

### How many benchmarks do Mistral Large 3 and Qwen2.5 72B Instruct share?

17 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Qwen2.5 72B Instruct has 43.