Model comparison
Devstral Small 2505 vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 34.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where Qwen3.5 Max Preview leads 30.8 to 19.7.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.3 | 45.3 |
| Released | 2025-05-07 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 4 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 Max Preview leads
Devstral Small 2505: 38.9 (#166), Qwen3.5 Max Preview: 44.0 (#77)
| Benchmark | Devstral Small 2505 | Qwen3.5 Max Preview |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1487 |
Reasoning Qwen3.5 Max Preview leads
Devstral Small 2505: 19.7 (#252), Qwen3.5 Max Preview: 30.8 (#84)
| Benchmark | Devstral Small 2505 | Qwen3.5 Max Preview |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1483 |
Math Not comparable
Devstral Small 2505: —, Qwen3.5 Max Preview: 40.1 (#94)
| Benchmark | Devstral Small 2505 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | — | 1474 |
Knowledge Not comparable
Devstral Small 2505: —, Qwen3.5 Max Preview: 41.8 (#107)
| Benchmark | Devstral Small 2505 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | — | 1489 |
Multilingual Not comparable
Devstral Small 2505: —, Qwen3.5 Max Preview: 56.2 (#22)
| Benchmark | Devstral Small 2505 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | — | 1465 |
| LMArena Chinese | — | 1534 |
| LMArena French | — | 1484 |
| LMArena German | — | 1487 |
| LMArena Japanese | — | 1495 |
| LMArena Korean | — | 1438 |
| LMArena Russian | — | 1471 |
| LMArena Spanish | — | 1470 |
Instruction Following Not comparable
Devstral Small 2505: —, Qwen3.5 Max Preview: 77.0 (#31)
| Benchmark | Devstral Small 2505 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | — | 1467 |
Long Context Not comparable
Devstral Small 2505: —, Qwen3.5 Max Preview: 45.2 (#45)
| Benchmark | Devstral Small 2505 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | — | 1476 |
Writing & Preference Not comparable
Devstral Small 2505: —, Qwen3.5 Max Preview: 66.0 (#41)
| Benchmark | Devstral Small 2505 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | — | 1470 |
| LMArena Creative Writing | — | 1464 |
| LMArena Multi-Turn | — | 1478 |
Frequently asked questions
Is Devstral Small 2505 better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 34.3 on the Noometry Index.
Is Devstral Small 2505 or Qwen3.5 Max Preview better for coding?
Qwen3.5 Max Preview scores higher on coding benchmarks: 44.0 versus 38.9 in the Noometry coding category.
How many benchmarks do Devstral Small 2505 and Qwen3.5 Max Preview share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Qwen3.5 Max Preview has 17.