# Mistral Small 3 vs Qwen1.5-72B

> Mistral Small 3 and Qwen1.5-72B score almost the same on the Noometry Index (30.9 vs 30.3), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/mistral-small-3-vs-qwen1-5-72b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Mistral Small 3 scores higher in 5 categories and Qwen1.5-72B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-72B leads 30.7 to 15.3.
- The biggest single-benchmark swing is GPQA Diamond: 47.3% for Mistral Small 3 and 28.8% for Qwen1.5-72B.

## Snapshot

| | Mistral Small 3 | Qwen1.5-72B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.9 | 30.3 |
| Rank | 268 | 282 |
| Context | 33K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.08 | — |
| Weights | Open | Open |

## Coding

- Mistral Small 3: 36.0 (#203)
- Qwen1.5-72B: 31.4 (#272)

| Benchmark | Mistral Small 3 | Qwen1.5-72B |
|---|---|---|
| BigCodeBench Instruct | 45.3% | 33.2% |
| LMArena Coding | 1246 | 1166 |
| BigCodeBench Complete | 50.4% | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |

## Reasoning

- Mistral Small 3: 18.2 (#269)
- Qwen1.5-72B: 21.2 (#201)

| Benchmark | Mistral Small 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1148 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 127.06 | — |

## Math

- Mistral Small 3: 15.3 (#290)
- Qwen1.5-72B: 30.7 (#205)

| Benchmark | Mistral Small 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1240 | 1164 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |

## Knowledge

- Mistral Small 3: 25.0 (#258)
- Qwen1.5-72B: 11.5 (#295)

| Benchmark | Mistral Small 3 | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 47.3% | 28.8% |
| LMArena Expert | 1202 | 1136 |
| Confabulations | 25.2% | — |

## Multilingual

- Mistral Small 3: 37.5 (#231)
- Qwen1.5-72B: 33.4 (#248)

| Benchmark | Mistral Small 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1198 | 1135 |
| LMArena Chinese | 1204 | 1186 |
| LMArena French | 1202 | 1158 |
| LMArena German | 1211 | 1084 |
| LMArena Japanese | 1111 | 1061 |
| LMArena Korean | 1188 | 1049 |
| LMArena Russian | 1216 | 1104 |
| LMArena Spanish | — | 1110 |

## Instruction Following

- Mistral Small 3: 63.9 (#224)
- Qwen1.5-72B: 59.6 (#251)

| Benchmark | Mistral Small 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1214 | 1142 |

## Long Context

- Mistral Small 3: 37.8 (#206)
- Qwen1.5-72B: 35.0 (#238)

| Benchmark | Mistral Small 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1246 | 1157 |

## Writing & Preference

- Mistral Small 3: 32.4 (#275)
- Qwen1.5-72B: 37.4 (#253)

| Benchmark | Mistral Small 3 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1234 | 1166 |
| LMArena Creative Writing | 1195 | 1137 |
| LMArena Multi-Turn | 1217 | 1160 |
| EQ-Bench Creative Writing | 707 | — |

## FAQ

### Is Mistral Small 3 better than Qwen1.5-72B?

Mistral Small 3 and Qwen1.5-72B score almost the same on the Noometry Index (30.9 vs 30.3), so choose on price, context window or the category you care about most.

### Is Mistral Small 3 or Qwen1.5-72B better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 31.4 in the Noometry coding category.

### How many benchmarks do Mistral Small 3 and Qwen1.5-72B share?

19 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen1.5-72B has 22.