Model comparison
Magistral Small vs Qwen3.5 27B
Qwen3.5 27B is the stronger model overall, scoring 41.4 to 29.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Magistral Small scores higher in 0 categories and Qwen3.5 27B in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 27B leads 26.6 to 6.9.
- The biggest single-benchmark swing is DTBench: 61.3% for Magistral Small and 82.4% for Qwen3.5 27B.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $0.30 / $2.40 for Qwen3.5 27B.
- Qwen3.5 27B accepts more context: 262K tokens versus 128K.
Side by side
| Magistral Small | Qwen3.5 27B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 29.9 | 41.4 |
| Released | 2025-06-10 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 40K | 66K |
| Input $ / M tokens | $0.50 | $0.30 |
| Output $ / M tokens | $1.50 | $2.40 |
| Results tracked | 10 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Magistral Small: 37.8 (#172), Qwen3.5 27B: 38.6 (#159)
| Benchmark | Magistral Small | Qwen3.5 27B |
|---|---|---|
| LMArena WebDev | — | 1357 |
| SciCode | 35.2% | — |
| WeirdML | — | 39.5% |
| LMArena Coding | — | 1427 |
| ALE-Bench | — | 349.45 |
Agentic & Tool Use Not comparable
Magistral Small: —, Qwen3.5 27B: —
| Benchmark | Magistral Small | Qwen3.5 27B |
|---|---|---|
| Vending-Bench 2 | — | 201.98 |
Reasoning Qwen3.5 27B leads
Magistral Small: 6.9 (#345), Qwen3.5 27B: 26.6 (#116)
| Benchmark | Magistral Small | Qwen3.5 27B |
|---|---|---|
| DTBench | 61.3% | 82.4% |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| NYT Connections (extended) | — | 47.9% |
| ARC-AGI-1 | 5% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 3% | — |
| Thematic Generalization | — | 45.5% |
| LMArena Hard Prompts | — | 1414 |
| LMCA | — | 34% |
| Epoch Capabilities Index | 133.19 | — |
Math Qwen3.5 27B leads
Magistral Small: 24.9 (#253), Qwen3.5 27B: 36.8 (#103)
| Benchmark | Magistral Small | Qwen3.5 27B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 56.7% |
| OTIS Mock AIME 2024-2025 | 30% | — |
| LMArena Math | — | 1428 |
Knowledge Qwen3.5 27B leads
Magistral Small: 30.9 (#215), Qwen3.5 27B: 37.4 (#149)
| Benchmark | Magistral Small | Qwen3.5 27B |
|---|---|---|
| GPQA Diamond | 56.1% | — |
| Vectara Hallucination Rate | — | 12.1% |
| LMArena Expert | — | 1428 |
Multimodal Not comparable
Magistral Small: —, Qwen3.5 27B: 38.7 (#56)
| Benchmark | Magistral Small | Qwen3.5 27B |
|---|---|---|
| LMArena Vision | — | 1240 |
Multilingual Not comparable
Magistral Small: —, Qwen3.5 27B: 51.0 (#112)
| Benchmark | Magistral Small | Qwen3.5 27B |
|---|---|---|
| LMArena Non-English | — | 1390 |
| LMArena Chinese | — | 1478 |
| LMArena French | — | 1409 |
| LMArena German | — | 1393 |
| LMArena Japanese | — | 1345 |
| LMArena Korean | — | 1359 |
| LMArena Russian | — | 1389 |
| LMArena Spanish | — | 1408 |
Instruction Following Not comparable
Magistral Small: —, Qwen3.5 27B: 73.7 (#114)
| Benchmark | Magistral Small | Qwen3.5 27B |
|---|---|---|
| LMArena Instruction Following | — | 1393 |
Long Context Not comparable
Magistral Small: —, Qwen3.5 27B: 43.1 (#103)
| Benchmark | Magistral Small | Qwen3.5 27B |
|---|---|---|
| LMArena Longer Query | — | 1413 |
Writing & Preference Not comparable
Magistral Small: —, Qwen3.5 27B: 59.5 (#106)
| Benchmark | Magistral Small | Qwen3.5 27B |
|---|---|---|
| LMArena Text | — | 1409 |
| LMArena Creative Writing | — | 1362 |
| LMArena Multi-Turn | — | 1410 |
Frequently asked questions
Is Magistral Small better than Qwen3.5 27B?
Qwen3.5 27B is the stronger model overall, scoring 41.4 to 29.9 on the Noometry Index.
Which is cheaper, Magistral Small or Qwen3.5 27B?
Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Qwen3.5 27B lists at $0.30 and $2.40.
Is Magistral Small or Qwen3.5 27B better for coding?
They score almost the same on coding (37.8 vs 38.6); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.5 27B does, with 262K tokens against 128K.
How many benchmarks do Magistral Small and Qwen3.5 27B share?
1 benchmark has published results for both models. Magistral Small has 10 scored results on Noometry and Qwen3.5 27B has 28.