Model comparison
Devstral Small 2505 vs Qwen3.5 122B-A10B
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 34.3 on the Noometry Index. Devstral Small 2505 costs 7.3× less per token, which makes it the better buy when Qwen3.5 122B-A10B'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 0 categories and Qwen3.5 122B-A10B in 2 categories; one gap is clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 122B-A10B leads 27.2 to 19.7.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 35.6% for Qwen3.5 122B-A10B.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
- Qwen3.5 122B-A10B accepts more context: 262K tokens versus 128K.
Side by side
| Devstral Small 2505 | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.3 | 42.1 |
| Released | 2025-05-07 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.10 | $0.40 |
| Output $ / M tokens | $0.30 | $3.20 |
| Results tracked | 4 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Devstral Small 2505: 38.9 (#166), Qwen3.5 122B-A10B: 39.1 (#162)
| Benchmark | Devstral Small 2505 | Qwen3.5 122B-A10B |
|---|---|---|
| SciCode | 28.8% | 35.6% |
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1360 |
| LMArena Coding | — | 1436 |
Reasoning Qwen3.5 122B-A10B leads
Devstral Small 2505: 19.7 (#252), Qwen3.5 122B-A10B: 27.2 (#123)
| Benchmark | Devstral Small 2505 | Qwen3.5 122B-A10B |
|---|---|---|
| CritPt | 0% | 0.9% |
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 51.7% |
| Thematic Generalization | — | 51.2% |
| LMArena Hard Prompts | — | 1421 |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84.3% |
| LMCA | — | 32.2% |
Math Not comparable
Devstral Small 2505: —, Qwen3.5 122B-A10B: 39.1 (#112)
| Benchmark | Devstral Small 2505 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | — | 1432 |
Knowledge Not comparable
Devstral Small 2505: —, Qwen3.5 122B-A10B: 38.8 (#142)
| Benchmark | Devstral Small 2505 | Qwen3.5 122B-A10B |
|---|---|---|
| Vectara Hallucination Rate | — | 11.2% |
| LMArena Expert | — | 1432 |
Multimodal Not comparable
Devstral Small 2505: —, Qwen3.5 122B-A10B: 39.6 (#57)
| Benchmark | Devstral Small 2505 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual Not comparable
Devstral Small 2505: —, Qwen3.5 122B-A10B: 51.6 (#107)
| Benchmark | Devstral Small 2505 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | — | 1400 |
| LMArena Chinese | — | 1462 |
| LMArena French | — | 1442 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1367 |
| LMArena Korean | — | 1352 |
| LMArena Russian | — | 1400 |
| LMArena Spanish | — | 1424 |
Instruction Following Not comparable
Devstral Small 2505: —, Qwen3.5 122B-A10B: 73.8 (#115)
| Benchmark | Devstral Small 2505 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | — | 1399 |
Long Context Not comparable
Devstral Small 2505: —, Qwen3.5 122B-A10B: 43.0 (#109)
| Benchmark | Devstral Small 2505 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | — | 1410 |
Writing & Preference Not comparable
Devstral Small 2505: —, Qwen3.5 122B-A10B: 60.0 (#105)
| Benchmark | Devstral Small 2505 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | — | 1417 |
| LMArena Creative Writing | — | 1368 |
| LMArena Multi-Turn | — | 1416 |
Frequently asked questions
Is Devstral Small 2505 better than Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 34.3 on the Noometry Index. Devstral Small 2505 costs 7.3× less per token, which makes it the better buy when Qwen3.5 122B-A10B's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or Qwen3.5 122B-A10B?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen3.5 122B-A10B lists at $0.40 and $3.20.
Is Devstral Small 2505 or Qwen3.5 122B-A10B better for coding?
They score almost the same on coding (38.9 vs 39.1); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.5 122B-A10B does, with 262K tokens against 128K.
How many benchmarks do Devstral Small 2505 and Qwen3.5 122B-A10B share?
2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Qwen3.5 122B-A10B has 27.