# Mistral Small 3 vs Qwen3.6 Plus

> Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 30.9 on the Noometry Index. Mistral Small 3 costs 20× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-small-3-vs-qwen3-6-plus
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and Qwen3.6 Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Plus leads 50.6 to 15.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for Mistral Small 3 and 93.3% for Qwen3.6 Plus.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Qwen3.6 Plus accepts more context: 1M tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Small 3 | Qwen3.6 Plus |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.9 | 47.3 |
| Rank | 268 | 54 |
| Context | 33K | 1M |
| Input $/M | $0.05 | $0.50 |
| Output $/M | $0.08 | $3 |
| Weights | Open | Proprietary |

## Coding

- Mistral Small 3: 36.0 (#203)
- Qwen3.6 Plus: 40.6 (#125)

| Benchmark | Mistral Small 3 | Qwen3.6 Plus |
|---|---|---|
| LMArena Coding | 1246 | 1467 |
| SWE-bench Verified | — | 57.9% |
| LMArena WebDev | — | 1461 |
| SciCode | — | 40.7% |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
| ALE-Bench | — | 670.15 |

## Agentic & Tool Use

- Mistral Small 3: —
- Qwen3.6 Plus: —

| Benchmark | Mistral Small 3 | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | — | 5,115 |

## Reasoning

- Mistral Small 3: 18.2 (#269)
- Qwen3.6 Plus: 28.5 (#89)

| Benchmark | Mistral Small 3 | Qwen3.6 Plus |
|---|---|---|
| Chess Puzzles | 0% | 17% |
| LMArena Hard Prompts | 1233 | 1449 |
| Epoch Capabilities Index | 127.06 | 147.67 |
| NYT Connections (extended) | — | 60.3% |
| CritPt | — | 2.9% |
| Thematic Generalization | — | 59.5% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 81.9% |
| LMCA | — | 33.1% |

## Math

- Mistral Small 3: 15.3 (#290)
- Qwen3.6 Plus: 50.6 (#44)

| Benchmark | Mistral Small 3 | Qwen3.6 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 93.3% |
| LMArena Math | 1240 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |

## Knowledge

- Mistral Small 3: 25.0 (#258)
- Qwen3.6 Plus: 56.1 (#40)

| Benchmark | Mistral Small 3 | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 47.3% | 88.4% |
| LMArena Expert | 1202 | 1456 |
| SimpleQA Verified | — | 44.1% |
| Confabulations | 25.2% | — |

## Multilingual

- Mistral Small 3: 37.5 (#231)
- Qwen3.6 Plus: 53.5 (#66)

| Benchmark | Mistral Small 3 | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1198 | 1424 |
| LMArena Chinese | 1204 | 1478 |
| LMArena French | 1202 | 1454 |
| LMArena German | 1211 | 1451 |
| LMArena Japanese | 1111 | 1389 |
| LMArena Korean | 1188 | 1381 |
| LMArena Russian | 1216 | 1434 |
| LMArena Spanish | — | 1432 |

## Instruction Following

- Mistral Small 3: 63.9 (#224)
- Qwen3.6 Plus: 75.2 (#70)

| Benchmark | Mistral Small 3 | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1214 | 1425 |

## Long Context

- Mistral Small 3: 37.8 (#206)
- Qwen3.6 Plus: 45.1 (#48)

| Benchmark | Mistral Small 3 | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1246 | 1440 |
| CL-bench | — | 20.3% |

## Writing & Preference

- Mistral Small 3: 32.4 (#275)
- Qwen3.6 Plus: 62.4 (#78)

| Benchmark | Mistral Small 3 | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1234 | 1437 |
| LMArena Creative Writing | 1195 | 1405 |
| LMArena Multi-Turn | 1217 | 1438 |
| EQ-Bench Creative Writing | 707 | — |

## FAQ

### Is Mistral Small 3 better than Qwen3.6 Plus?

Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 30.9 on the Noometry Index. Mistral Small 3 costs 20× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.

### Which is cheaper, Mistral Small 3 or Qwen3.6 Plus?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.

### Is Mistral Small 3 or Qwen3.6 Plus better for coding?

Qwen3.6 Plus scores higher on coding benchmarks: 40.6 versus 36.0 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.6 Plus does, with 1M tokens against 33K.

### How many benchmarks do Mistral Small 3 and Qwen3.6 Plus share?

20 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen3.6 Plus has 37.