# Mistral Small 3 vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.8 to 31.2 on the Noometry Index. Mistral Small 3 costs 52× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/mistral-small-3-vs-qwen3-8-max
- 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 Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 16.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for Mistral Small 3 and 100% for Qwen3.8 Max.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 33K.
- Mistral Small 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Mistral Small 3 | Qwen3.8 Max |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.2 | 56.8 |
| Rank | 278 | 22 |
| Context | 33K | 1M |
| Input $/M | $0.05 | $2 |
| Output $/M | $0.08 | $6 |
| Weights | Open | Proprietary |

## Coding

- Mistral Small 3: 36.5 (#207)
- Qwen3.8 Max: 53.5 (#29)

| Benchmark | Mistral Small 3 | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1246 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |

## Agentic & Tool Use

- Mistral Small 3: —
- Qwen3.8 Max: 45.4 (#14)

| Benchmark | Mistral Small 3 | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |

## Reasoning

- Mistral Small 3: 18.9 (#273)
- Qwen3.8 Max: 54.4 (#26)

| Benchmark | Mistral Small 3 | Qwen3.8 Max |
|---|---|---|
| Chess Puzzles | 0% | 40% |
| LMArena Hard Prompts | 1233 | 1496 |
| Epoch Capabilities Index | 127.07 | 156.41 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |

## Math

- Mistral Small 3: 16.3 (#295)
- Qwen3.8 Max: 73.2 (#20)

| Benchmark | Mistral Small 3 | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 100% |
| LMArena Math | 1240 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |

## Knowledge

- Mistral Small 3: 25.1 (#263)
- Qwen3.8 Max: 61.7 (#27)

| Benchmark | Mistral Small 3 | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 47.3% | 92.7% |
| LMArena Expert | 1202 | 1507 |
| SimpleQA Verified | — | 47.3% |
| Confabulations | 25.2% | — |

## Multimodal

- Mistral Small 3: —
- Qwen3.8 Max: 37.2 (#75)

| Benchmark | Mistral Small 3 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |

## Multilingual

- Mistral Small 3: 37.3 (#236)
- Qwen3.8 Max: 56.7 (#18)

| Benchmark | Mistral Small 3 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1198 | 1472 |
| LMArena Chinese | 1204 | 1538 |
| LMArena French | 1203 | 1503 |
| LMArena German | 1211 | 1483 |
| LMArena Japanese | 1111 | 1467 |
| LMArena Korean | 1188 | 1461 |
| LMArena Russian | 1216 | 1481 |
| LMArena Spanish | — | 1492 |

## Instruction Following

- Mistral Small 3: 63.7 (#229)
- Qwen3.8 Max: 77.6 (#17)

| Benchmark | Mistral Small 3 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1214 | 1479 |

## Long Context

- Mistral Small 3: 37.8 (#211)
- Qwen3.8 Max: 45.6 (#31)

| Benchmark | Mistral Small 3 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1246 | 1489 |

## Writing & Preference

- Mistral Small 3: 32.2 (#280)
- Qwen3.8 Max: 67.1 (#30)

| Benchmark | Mistral Small 3 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1234 | 1483 |
| LMArena Creative Writing | 1195 | 1479 |
| LMArena Multi-Turn | 1217 | 1489 |
| EQ-Bench Creative Writing | 707 | — |

## FAQ

### Is Mistral Small 3 better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 31.2 on the Noometry Index. Mistral Small 3 costs 52× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

### Which is cheaper, Mistral Small 3 or Qwen3.8 Max?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen3.8 Max lists at $2 and $6.

### Is Mistral Small 3 or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 36.5 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.8 Max does, with 1M tokens against 33K.

### How many benchmarks do Mistral Small 3 and Qwen3.8 Max share?

20 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen3.8 Max has 39.