Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Devstral Small 2505
Devstral Small 2505 has enough public results to be ranked (#228); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeek
Mistral AISide by side
| DeepSeek-V2 (MoE-236B, May 2024) | Devstral Small 2505 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 39.7 | 33.9 |
| Released | 2024-05-07 | 2025-05-07 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 10 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141), Devstral Small 2505: 38.6 (#160)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Devstral Small 2505 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 56.4% |
| SciCode | — | 28.8% |
| BigCodeBench Instruct | 48.9% | — |
| BigCodeBench Complete | 59.4% | — |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Devstral Small 2505: 19.1 (#243)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Devstral Small 2505 |
|---|---|---|
| Kagi LLM Benchmark | — | 37.7% |
| CritPt | — | 0% |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.78 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Devstral Small 2505: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Devstral Small 2505 |
|---|---|---|
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Devstral Small 2505?
Devstral Small 2505 has enough public results to be ranked (#228); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Devstral Small 2505 better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 38.6 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Devstral Small 2505 share?
0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Devstral Small 2505 has 4.