# Mistral Small vs Qwen2-72B

> Mistral Small is the stronger model overall, scoring 33.4 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-small-vs-qwen2-72b
- Last updated: 2026-10-12
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Mistral Small scores higher in 7 categories and Qwen2-72B in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 30.2 to 16.4.
- The biggest single-benchmark swing is MATH Level 5: 46.8% for Mistral Small and 39.1% for Qwen2-72B.

## Snapshot

| | Mistral Small | Qwen2-72B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 30.0 |
| Rank | 243 | 300 |
| Context | 262K | — |
| Input $/M | $0.15 | — |
| Output $/M | $0.60 | — |
| Weights | Open | Open |

## Coding

- Mistral Small: 34.0 (#247)
- Qwen2-72B: 29.1 (#310)

| Benchmark | Mistral Small | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 36.1% | 38.5% |
| LMArena Coding | 1362 | 1196 |
| BigCodeBench Complete | 46.6% | 54% |
| SciCode | 26.5% | — |
| WeirdML | — | 11.3% |
| LiveBench Coding | 36.2% | — |
| ALE-Bench | 497.62 | — |

## Agentic & Tool Use

- Mistral Small: 28.1 (#93)
- Qwen2-72B: 17.0 (#146)

| Benchmark | Mistral Small | Qwen2-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Mistral Small: 19.8 (#250)
- Qwen2-72B: 23.2 (#181)

| Benchmark | Mistral Small | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1335 | 1191 |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 44.8% | — |
| DTBench | 70.9% | — |
| LiveBench Data Analysis | 53.7% | — |
| LMCA | 20.6% | — |
| Epoch Capabilities Index | — | 125.28 |
| LiveBench | 44% | — |

## Math

- Mistral Small: 16.4 (#293)
- Qwen2-72B: 30.2 (#236)

| Benchmark | Mistral Small | Qwen2-72B |
|---|---|---|
| LMArena Math | 1341 | 1235 |
| MATH Level 5 | 46.8% | 39.1% |
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| LiveBench Math | 39.9% | — |

## Knowledge

- Mistral Small: 31.0 (#222)
- Qwen2-72B: 21.2 (#275)

| Benchmark | Mistral Small | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 47.5% | 40.8% |
| LMArena Expert | 1291 | 1171 |
| MMLU | 68.7% | 82.4% |
| Vectara Hallucination Rate | 5.1% | — |

## Multimodal

- Mistral Small: 33.5 (#96)
- Qwen2-72B: —

| Benchmark | Mistral Small | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1142 | — |

## Multilingual

- Mistral Small: 45.5 (#169)
- Qwen2-72B: 35.9 (#244)

| Benchmark | Mistral Small | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1315 | 1176 |
| LMArena Chinese | 1340 | 1240 |
| LMArena French | 1337 | 1170 |
| LMArena German | 1340 | 1151 |
| LMArena Japanese | 1275 | 1111 |
| LMArena Korean | 1259 | 1083 |
| LMArena Russian | 1324 | 1169 |
| LMArena Spanish | 1346 | 1169 |

## Instruction Following

- Mistral Small: 66.4 (#209)
- Qwen2-72B: 61.7 (#241)

| Benchmark | Mistral Small | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1310 | 1181 |
| LiveBench Instruction Following | 63.7% | — |

## Long Context

- Mistral Small: 40.4 (#156)
- Qwen2-72B: 36.1 (#235)

| Benchmark | Mistral Small | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1327 | 1192 |

## Writing & Preference

- Mistral Small: 52.5 (#171)
- Qwen2-72B: 40.8 (#241)

| Benchmark | Mistral Small | Qwen2-72B |
|---|---|---|
| LMArena Text | 1338 | 1203 |
| LMArena Creative Writing | 1305 | 1181 |
| LMArena Multi-Turn | 1344 | 1196 |
| LiveBench Language | 30.5% | — |

## FAQ

### Is Mistral Small better than Qwen2-72B?

Mistral Small is the stronger model overall, scoring 33.4 to 30.0 on the Noometry Index.

### Is Mistral Small or Qwen2-72B better for coding?

Mistral Small scores higher on coding benchmarks: 34.0 versus 29.1 in the Noometry coding category.

### How many benchmarks do Mistral Small and Qwen2-72B share?

22 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen2-72B has 26.