# Mistral Small 3 vs Qwen2.5 72B Instruct

> Mistral Small 3 and Qwen2.5 72B Instruct score almost the same on the Noometry Index (30.9 vs 31.5), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/mistral-small-3-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Mistral Small 3 scores higher in 1 category and Qwen2.5 72B Instruct in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.9 to 32.4.
- The biggest single-benchmark swing is Confabulations: 25.2% for Mistral Small 3 and 19.1% for Qwen2.5 72B Instruct.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct accepts more context: 131K tokens versus 33K.

## Snapshot

| | Mistral Small 3 | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.9 | 31.5 |
| Rank | 268 | 259 |
| Context | 33K | 131K |
| Input $/M | $0.05 | $1.40 |
| Output $/M | $0.08 | $5.60 |
| Weights | Open | Open |

## Coding

- Mistral Small 3: 36.0 (#203)
- Qwen2.5 72B Instruct: 32.8 (#256)

| Benchmark | Mistral Small 3 | Qwen2.5 72B Instruct |
|---|---|---|
| BigCodeBench Instruct | 45.3% | 45.8% |
| LMArena Coding | 1246 | 1293 |
| BigCodeBench Complete | 50.4% | 55.9% |
| WeirdML | — | 16% |

## Agentic & Tool Use

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

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

## Reasoning

- Mistral Small 3: 18.2 (#269)
- Qwen2.5 72B Instruct: 21.4 (#197)

| Benchmark | Mistral Small 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1271 |
| Epoch Capabilities Index | 127.06 | 129.01 |
| Chess Puzzles | 0% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Mistral Small 3: 15.3 (#290)
- Qwen2.5 72B Instruct: 18.1 (#281)

| Benchmark | Mistral Small 3 | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 8.1% |
| LMArena Math | 1240 | 1283 |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |

## Knowledge

- Mistral Small 3: 25.0 (#258)
- Qwen2.5 72B Instruct: 26.9 (#247)

| Benchmark | Mistral Small 3 | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 47.3% | 49.1% |
| Confabulations | 25.2% | 19.1% |
| LMArena Expert | 1202 | 1245 |
| MMLU-Pro | — | 63.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multilingual

- Mistral Small 3: 37.5 (#231)
- Qwen2.5 72B Instruct: 41.2 (#208)

| Benchmark | Mistral Small 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1198 | 1252 |
| LMArena Chinese | 1204 | 1272 |
| LMArena French | 1202 | 1279 |
| LMArena German | 1211 | 1234 |
| LMArena Japanese | 1111 | 1180 |
| LMArena Korean | 1188 | 1188 |
| LMArena Russian | 1216 | 1264 |
| LMArena Spanish | — | 1255 |

## Instruction Following

- Mistral Small 3: 63.9 (#224)
- Qwen2.5 72B Instruct: 65.7 (#216)

| Benchmark | Mistral Small 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1214 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Mistral Small 3: 37.8 (#206)
- Qwen2.5 72B Instruct: 38.9 (#183)

| Benchmark | Mistral Small 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1246 | 1282 |

## Writing & Preference

- Mistral Small 3: 32.4 (#275)
- Qwen2.5 72B Instruct: 46.9 (#210)

| Benchmark | Mistral Small 3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1234 | 1269 |
| LMArena Creative Writing | 1195 | 1221 |
| LMArena Multi-Turn | 1217 | 1272 |
| EQ-Bench Creative Writing | 707 | — |
| WildBench | — | 80.2% |

## FAQ

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

Mistral Small 3 and Qwen2.5 72B Instruct score almost the same on the Noometry Index (30.9 vs 31.5), so choose on price, context window or the category you care about most.

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

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

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

Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 32.8 in the Noometry coding category.

### Which has the bigger context window?

Qwen2.5 72B Instruct does, with 131K tokens against 33K.

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

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