Model comparison
Devstral Small 2505 vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 34.3 on the Noometry Index. Devstral Small 2505 costs 4.0× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Devstral Small 2505 scores higher in 1 category and Qwen Plus in 1 category; one gap is clear of the uncertainty.
- The widest gap is in reasoning, where Qwen Plus leads 28.4 to 19.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.7% for Devstral Small 2505 and 63.3% for Qwen Plus.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen Plus accepts more context: 1M tokens versus 128K.
- Devstral Small 2505 has downloadable open weights; the other is API-only.
Side by side
| Devstral Small 2505 | Qwen Plus | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.3 | 37.1 |
| Released | 2025-05-07 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 128K | 33K |
| Input $ / M tokens | $0.10 | $0.40 |
| Output $ / M tokens | $0.30 | $1.20 |
| Results tracked | 4 | 20 |
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), Qwen Plus: 38.9 (#167)
| Benchmark | Devstral Small 2505 | Qwen Plus |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1328 |
Reasoning Qwen Plus leads
Devstral Small 2505: 19.7 (#252), Qwen Plus: 28.4 (#107)
| Benchmark | Devstral Small 2505 | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | 63.3% |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1317 |
| DTBench | — | 81.1% |
| LMCA | — | 24% |
Math Not comparable
Devstral Small 2505: —, Qwen Plus: 23.3 (#271)
| Benchmark | Devstral Small 2505 | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 17.8% |
| LMArena Math | — | 1326 |
| MATH Level 5 | — | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Not comparable
Devstral Small 2505: —, Qwen Plus: 27.4 (#251)
| Benchmark | Devstral Small 2505 | Qwen Plus |
|---|---|---|
| GPQA Diamond | — | 48.1% |
| LMArena Expert | — | 1328 |
Multilingual Not comparable
Devstral Small 2505: —, Qwen Plus: 45.1 (#175)
| Benchmark | Devstral Small 2505 | Qwen Plus |
|---|---|---|
| LMArena Non-English | — | 1310 |
| LMArena Chinese | — | 1347 |
| LMArena Japanese | — | 1251 |
| LMArena Russian | — | 1323 |
Instruction Following Not comparable
Devstral Small 2505: —, Qwen Plus: 68.8 (#181)
| Benchmark | Devstral Small 2505 | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | — | 1303 |
Long Context Not comparable
Devstral Small 2505: —, Qwen Plus: 40.3 (#158)
| Benchmark | Devstral Small 2505 | Qwen Plus |
|---|---|---|
| LMArena Longer Query | — | 1324 |
Writing & Preference Not comparable
Devstral Small 2505: —, Qwen Plus: 52.2 (#176)
| Benchmark | Devstral Small 2505 | Qwen Plus |
|---|---|---|
| LMArena Text | — | 1326 |
| LMArena Creative Writing | — | 1293 |
| LMArena Multi-Turn | — | 1336 |
Frequently asked questions
Is Devstral Small 2505 better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 34.3 on the Noometry Index. Devstral Small 2505 costs 4.0× less per token, which makes it the better buy when Qwen Plus's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or Qwen Plus?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen Plus lists at $0.40 and $1.20.
Is Devstral Small 2505 or Qwen Plus better for coding?
They score almost the same on coding (38.9 vs 38.9); test both on your own repository before choosing.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 128K.
How many benchmarks do Devstral Small 2505 and Qwen Plus share?
1 benchmark has published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Qwen Plus has 20.