Model comparison
DeepSeek-R1-Distill-Qwen-14B vs Devstral Small 2505
Devstral Small 2505 is the stronger model overall, scoring 33.9 to 32.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
Mistral AISide by side
| DeepSeek-R1-Distill-Qwen-14B | Devstral Small 2505 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 32.2 | 33.9 |
| Released | 2025-01-20 | 2025-05-07 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 7 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Devstral Small 2505 leads
DeepSeek-R1-Distill-Qwen-14B: 36.3 (#196), Devstral Small 2505: 38.6 (#160)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | Devstral Small 2505 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 56.4% |
| SciCode | — | 28.8% |
| BigCodeBench Instruct | 38.1% | — |
| BigCodeBench Complete | 48.4% | — |
Reasoning Too close to call
DeepSeek-R1-Distill-Qwen-14B: 18.5 (#259), Devstral Small 2505: 19.1 (#243)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | Devstral Small 2505 |
|---|---|---|
| Kagi LLM Benchmark | — | 37.7% |
| CritPt | — | 0% |
| Chess Puzzles | 1% | — |
| Epoch Capabilities Index | 135.43 | — |
Math Not comparable
DeepSeek-R1-Distill-Qwen-14B: 33.9 (#164), Devstral Small 2505: —
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | Devstral Small 2505 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 50.6% | — |
| MATH Level 5 | 87.1% | — |
Knowledge Not comparable
DeepSeek-R1-Distill-Qwen-14B: 24.1 (#265), Devstral Small 2505: —
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | Devstral Small 2505 |
|---|---|---|
| GPQA Diamond | 44.7% | — |
Frequently asked questions
Is DeepSeek-R1-Distill-Qwen-14B better than Devstral Small 2505?
Devstral Small 2505 is the stronger model overall, scoring 33.9 to 32.2 on the Noometry Index.
Is DeepSeek-R1-Distill-Qwen-14B or Devstral Small 2505 better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.6 versus 36.3 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Qwen-14B and Devstral Small 2505 share?
0 benchmarks have published results for both models. DeepSeek-R1-Distill-Qwen-14B has 7 scored results on Noometry and Devstral Small 2505 has 4.