Model comparison
Devstral Small 2505 vs Qwen3.6 35B-A3B
Qwen3.6 35B-A3B is the stronger model overall, scoring 37.6 to 34.3 on the Noometry Index. Devstral Small 2505 costs 3.7× less per token, which makes it the better buy when Qwen3.6 35B-A3B's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. Devstral Small 2505 scores higher in 1 category and Qwen3.6 35B-A3B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.6 35B-A3B leads 28.0 to 19.7.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 35.8% for Qwen3.6 35B-A3B.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.25 / $1.49 for Qwen3.6 35B-A3B.
- Qwen3.6 35B-A3B accepts more context: 262K tokens versus 128K.
Side by side
| Devstral Small 2505 | Qwen3.6 35B-A3B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.3 | 37.6 |
| Released | 2025-05-07 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.10 | $0.25 |
| Output $ / M tokens | $0.30 | $1.49 |
| Results tracked | 4 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Devstral Small 2505 leads
Devstral Small 2505: 38.9 (#166), Qwen3.6 35B-A3B: 37.2 (#196)
| Benchmark | Devstral Small 2505 | Qwen3.6 35B-A3B |
|---|---|---|
| SciCode | 28.8% | 35.8% |
| SWE-bench Verified (bash only) | 56.4% | — |
| WeirdML | — | 34.5% |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, Qwen3.6 35B-A3B: 22.1 (#134)
| Benchmark | Devstral Small 2505 | Qwen3.6 35B-A3B |
|---|---|---|
| Terminal-Bench | — | 23% |
Reasoning Qwen3.6 35B-A3B leads
Devstral Small 2505: 19.7 (#252), Qwen3.6 35B-A3B: 28.0 (#109)
| Benchmark | Devstral Small 2505 | Qwen3.6 35B-A3B |
|---|---|---|
| CritPt | 0% | 0.3% |
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 41.6% |
| Chess Puzzles | — | 26% |
| Mystery Game Puzzles | — | 22% |
| DTBench | — | 73.9% |
| LMCA | — | 29.7% |
| Surface Evolver Bench | — | 44.4% |
| Epoch Capabilities Index | — | 143.93 |
Math Not comparable
Devstral Small 2505: —, Qwen3.6 35B-A3B: 38.9 (#121)
| Benchmark | Devstral Small 2505 | Qwen3.6 35B-A3B |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 20.4% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
Knowledge Not comparable
Devstral Small 2505: —, Qwen3.6 35B-A3B: 51.3 (#68)
| Benchmark | Devstral Small 2505 | Qwen3.6 35B-A3B |
|---|---|---|
| GPQA Diamond | — | 84.8% |
Frequently asked questions
Is Devstral Small 2505 better than Qwen3.6 35B-A3B?
Qwen3.6 35B-A3B is the stronger model overall, scoring 37.6 to 34.3 on the Noometry Index. Devstral Small 2505 costs 3.7× less per token, which makes it the better buy when Qwen3.6 35B-A3B's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or Qwen3.6 35B-A3B?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen3.6 35B-A3B lists at $0.25 and $1.49.
Is Devstral Small 2505 or Qwen3.6 35B-A3B better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 37.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 35B-A3B does, with 262K tokens against 128K.
How many benchmarks do Devstral Small 2505 and Qwen3.6 35B-A3B share?
2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Qwen3.6 35B-A3B has 14.