# Magistral Small vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.8 to 30.2 on the Noometry Index. Magistral Small costs 4.0× 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/magistral-small-vs-qwen3-8-max
- Last updated: 2026-10-12
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. Magistral Small scores higher in 0 categories and Qwen3.8 Max in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.8 Max leads 54.4 to 6.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 30% for Magistral Small and 100% for Qwen3.8 Max.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 128K.
- Magistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | Magistral Small | Qwen3.8 Max |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.2 | 56.8 |
| Rank | 296 | 22 |
| Context | 128K | 1M |
| Input $/M | $0.50 | $2 |
| Output $/M | $1.50 | $6 |
| Weights | Open | Proprietary |

## Coding

- Magistral Small: 38.4 (#176)
- Qwen3.8 Max: 53.5 (#29)

| Benchmark | Magistral Small | Qwen3.8 Max |
|---|---|---|
| SciCode | 35.2% | 53.2% |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| LMArena Coding | — | 1502 |

## Agentic & Tool Use

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

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

## Reasoning

- Magistral Small: 6.8 (#350)
- Qwen3.8 Max: 54.4 (#26)

| Benchmark | Magistral Small | Qwen3.8 Max |
|---|---|---|
| CritPt | 0.3% | 20% |
| Chess Puzzles | 3% | 40% |
| DTBench | 61.3% | 92% |
| Epoch Capabilities Index | 133.19 | 156.41 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| NYT Connections (extended) | — | 88.3% |
| ARC-AGI-1 | 5% | — |
| LMArena Hard Prompts | — | 1496 |
| Mystery Game Puzzles | — | 38% |
| LMCA | — | 46.2% |

## Math

- Magistral Small: 26.2 (#261)
- Qwen3.8 Max: 73.2 (#20)

| Benchmark | Magistral Small | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | 100% |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| LMArena Math | — | 1499 |

## Knowledge

- Magistral Small: 30.9 (#223)
- Qwen3.8 Max: 61.7 (#27)

| Benchmark | Magistral Small | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 56.1% | 92.7% |
| SimpleQA Verified | — | 47.3% |
| LMArena Expert | — | 1507 |

## Multimodal

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

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

## Multilingual

- Magistral Small: —
- Qwen3.8 Max: 56.7 (#18)

| Benchmark | Magistral Small | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | — | 1472 |
| LMArena Chinese | — | 1538 |
| LMArena French | — | 1503 |
| LMArena German | — | 1483 |
| LMArena Japanese | — | 1467 |
| LMArena Korean | — | 1461 |
| LMArena Russian | — | 1481 |
| LMArena Spanish | — | 1492 |

## Instruction Following

- Magistral Small: —
- Qwen3.8 Max: 77.6 (#17)

| Benchmark | Magistral Small | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | — | 1479 |

## Long Context

- Magistral Small: —
- Qwen3.8 Max: 45.6 (#31)

| Benchmark | Magistral Small | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | — | 1489 |

## Writing & Preference

- Magistral Small: —
- Qwen3.8 Max: 67.1 (#30)

| Benchmark | Magistral Small | Qwen3.8 Max |
|---|---|---|
| LMArena Text | — | 1483 |
| LMArena Creative Writing | — | 1479 |
| LMArena Multi-Turn | — | 1489 |

## FAQ

### Is Magistral Small better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 30.2 on the Noometry Index. Magistral Small costs 4.0× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

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

Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Qwen3.8 Max lists at $2 and $6.

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

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 38.4 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.8 Max does, with 1M tokens against 128K.

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

7 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Qwen3.8 Max has 39.