# Mistral Small vs Qwen2.5 7B Instruct

> Mistral Small is the stronger model overall, scoring 33.4 to 29.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-small-vs-qwen2-5-7b-instruct
- Last updated: 2026-10-11
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. Mistral Small scores higher in 6 categories and Qwen2.5 7B Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small leads 31.0 to 17.0.
- The biggest single-benchmark swing is DTBench: 70.9% for Mistral Small and 47.7% for Qwen2.5 7B Instruct.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.17 / $0.70 for Qwen2.5 7B Instruct.
- Mistral Small accepts more context: 262K tokens versus 131K.

## Snapshot

| | Mistral Small | Qwen2.5 7B Instruct |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 29.0 |
| Rank | 243 | 320 |
| Context | 262K | 131K |
| Input $/M | $0.15 | $0.17 |
| Output $/M | $0.60 | $0.70 |
| Weights | Open | Open |

## Coding

- Mistral Small: 34.0 (#247)
- Qwen2.5 7B Instruct: 36.5 (#208)

| Benchmark | Mistral Small | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | 36.1% | 37.6% |
| BigCodeBench Complete | 46.6% | 46.1% |
| SciCode | 26.5% | — |
| LiveBench Coding | 36.2% | — |
| LMArena Coding | 1362 | — |
| ALE-Bench | 497.62 | — |

## Agentic & Tool Use

- Mistral Small: 28.1 (#93)
- Qwen2.5 7B Instruct: 23.8 (#124)

| Benchmark | Mistral Small | Qwen2.5 7B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
| BALROG | — | 7.8% |

## Reasoning

- Mistral Small: 19.8 (#250)
- Qwen2.5 7B Instruct: 14.8 (#322)

| Benchmark | Mistral Small | Qwen2.5 7B Instruct |
|---|---|---|
| DTBench | 70.9% | 47.7% |
| LMCA | 20.6% | 6.4% |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 44.8% | — |
| LMArena Hard Prompts | 1335 | — |
| LiveBench Data Analysis | 53.7% | — |
| Epoch Capabilities Index | — | 118.51 |
| LiveBench | 44% | — |

## Math

- Mistral Small: 16.4 (#293)
- Qwen2.5 7B Instruct: 12.6 (#306)

| Benchmark | Mistral Small | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 5.8% | 2.5% |
| Omni-MATH | — | 29.4% |
| LiveBench Math | 39.9% | — |
| LMArena Math | 1341 | — |
| MATH Level 5 | 46.8% | — |

## Knowledge

- Mistral Small: 31.0 (#222)
- Qwen2.5 7B Instruct: 17.0 (#286)

| Benchmark | Mistral Small | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 47.5% | 35.5% |
| MMLU | 68.7% | 72.9% |
| MMLU-Pro | — | 53.9% |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1291 | — |

## Multimodal

- Mistral Small: 33.5 (#96)
- Qwen2.5 7B Instruct: —

| Benchmark | Mistral Small | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Vision | 1142 | — |

## Multilingual

- Mistral Small: 45.5 (#169)
- Qwen2.5 7B Instruct: —

| Benchmark | Mistral Small | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1315 | — |
| LMArena Chinese | 1340 | — |
| LMArena French | 1337 | — |
| LMArena German | 1340 | — |
| LMArena Japanese | 1275 | — |
| LMArena Korean | 1259 | — |
| LMArena Russian | 1324 | — |
| LMArena Spanish | 1346 | — |

## Instruction Following

- Mistral Small: 66.4 (#209)
- Qwen2.5 7B Instruct: 63.2 (#231)

| Benchmark | Mistral Small | Qwen2.5 7B Instruct |
|---|---|---|
| LiveBench Instruction Following | 63.7% | — |
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1310 | — |

## Long Context

- Mistral Small: 40.4 (#156)
- Qwen2.5 7B Instruct: —

| Benchmark | Mistral Small | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1327 | — |

## Writing & Preference

- Mistral Small: 52.5 (#171)
- Qwen2.5 7B Instruct: 48.8 (#195)

| Benchmark | Mistral Small | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1338 | — |
| LMArena Creative Writing | 1305 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1344 | — |
| LiveBench Language | 30.5% | — |

## FAQ

### Is Mistral Small better than Qwen2.5 7B Instruct?

Mistral Small is the stronger model overall, scoring 33.4 to 29.0 on the Noometry Index.

### Which is cheaper, Mistral Small or Qwen2.5 7B Instruct?

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen2.5 7B Instruct lists at $0.17 and $0.70.

### Is Mistral Small or Qwen2.5 7B Instruct better for coding?

Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 34.0 in the Noometry coding category.

### Which has the bigger context window?

Mistral Small does, with 262K tokens against 131K.

### How many benchmarks do Mistral Small and Qwen2.5 7B Instruct share?

7 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen2.5 7B Instruct has 15.