Model comparison
Devstral Small 2505 vs Qwen2.5 7B Instruct
Devstral Small 2505 is the stronger model overall, scoring 34.3 to 29.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where Devstral Small 2505 leads 19.7 to 14.8.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.17 / $0.70 for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| Devstral Small 2505 | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 34.3 | 29.0 |
| Released | 2025-05-07 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.10 | $0.17 |
| Output $ / M tokens | $0.30 | $0.70 |
| Results tracked | 4 | 15 |
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), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Devstral Small 2505 | Qwen2.5 7B Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 46.1% |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Devstral Small 2505 | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Devstral Small 2505 leads
Devstral Small 2505: 19.7 (#252), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Devstral Small 2505 | Qwen2.5 7B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| Epoch Capabilities Index | — | 118.51 |
Math Not comparable
Devstral Small 2505: —, Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Devstral Small 2505 | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
Knowledge Not comparable
Devstral Small 2505: —, Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Devstral Small 2505 | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| MMLU | — | 72.9% |
Instruction Following Not comparable
Devstral Small 2505: —, Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Devstral Small 2505 | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
Writing & Preference Not comparable
Devstral Small 2505: —, Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Devstral Small 2505 | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | — | 73.1% |
Frequently asked questions
Is Devstral Small 2505 better than Qwen2.5 7B Instruct?
Devstral Small 2505 is the stronger model overall, scoring 34.3 to 29.0 on the Noometry Index.
Which is cheaper, Devstral Small 2505 or Qwen2.5 7B Instruct?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen2.5 7B Instruct lists at $0.17 and $0.70.
Is Devstral Small 2505 or Qwen2.5 7B Instruct better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5 7B Instruct does, with 131K tokens against 128K.
How many benchmarks do Devstral Small 2505 and Qwen2.5 7B Instruct share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Qwen2.5 7B Instruct has 15.