Model comparison
Devstral Small 2505 vs Qwen3-4B
Devstral Small 2505 is the stronger model overall, scoring 33.9 to 31.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
Side by side
| Devstral Small 2505 | Qwen3-4B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.9 | 31.5 |
| Released | 2025-05-07 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 4 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Devstral Small 2505: 38.6 (#160), Qwen3-4B: —
| Benchmark | Devstral Small 2505 | Qwen3-4B |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, Qwen3-4B: 27.3 (#94)
| Benchmark | Devstral Small 2505 | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning Too close to call
Devstral Small 2505: 19.1 (#243), Qwen3-4B: 18.5 (#264)
| Benchmark | Devstral Small 2505 | Qwen3-4B |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 4% |
Math Not comparable
Devstral Small 2505: —, Qwen3-4B: 28.5 (#228)
| Benchmark | Devstral Small 2505 | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
Knowledge Not comparable
Devstral Small 2505: —, Qwen3-4B: 33.0 (#198)
| Benchmark | Devstral Small 2505 | Qwen3-4B |
|---|---|---|
| GPQA Diamond | — | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
Frequently asked questions
Is Devstral Small 2505 better than Qwen3-4B?
Devstral Small 2505 is the stronger model overall, scoring 33.9 to 31.5 on the Noometry Index.
How many benchmarks do Devstral Small 2505 and Qwen3-4B share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Qwen3-4B has 6.