Model comparison
Deepseek Coder v2 vs Devstral Small 2505
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 34.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
Mistral AISummary
- The widest gap is in reasoning, where Deepseek Coder v2 leads 23.6 to 19.7.
Side by side
| Deepseek Coder v2 | Devstral Small 2505 | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 35.9 | 34.3 |
| Released | 2024-06-17 | 2025-05-07 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 24 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Deepseek Coder v2: 38.1 (#183), Devstral Small 2505: 38.9 (#166)
| Benchmark | Deepseek Coder v2 | Devstral Small 2505 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 56.4% |
| SciCode | — | 28.8% |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1251 | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Devstral Small 2505: 19.7 (#252)
| Benchmark | Deepseek Coder v2 | Devstral Small 2505 |
|---|---|---|
| Kagi LLM Benchmark | — | 37.7% |
| CritPt | — | 0% |
| LMArena Hard Prompts | 1207 | — |
| WinoGrande | 83.7% | — |
Math Not comparable
Deepseek Coder v2: 34.9 (#190), Devstral Small 2505: —
| Benchmark | Deepseek Coder v2 | Devstral Small 2505 |
|---|---|---|
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |
Knowledge Not comparable
Deepseek Coder v2: 32.3 (#212), Devstral Small 2505: —
| Benchmark | Deepseek Coder v2 | Devstral Small 2505 |
|---|---|---|
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Not comparable
Deepseek Coder v2: 36.3 (#240), Devstral Small 2505: —
| Benchmark | Deepseek Coder v2 | Devstral Small 2505 |
|---|---|---|
| LMArena Non-English | 1182 | — |
| LMArena Chinese | 1201 | — |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Not comparable
Deepseek Coder v2: 61.7 (#242), Devstral Small 2505: —
| Benchmark | Deepseek Coder v2 | Devstral Small 2505 |
|---|---|---|
| LMArena Instruction Following | 1180 | — |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#224), Devstral Small 2505: —
| Benchmark | Deepseek Coder v2 | Devstral Small 2505 |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference Not comparable
Deepseek Coder v2: 38.2 (#253), Devstral Small 2505: —
| Benchmark | Deepseek Coder v2 | Devstral Small 2505 |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| LMArena Multi-Turn | 1177 | — |
Frequently asked questions
Is Deepseek Coder v2 better than Devstral Small 2505?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 34.3 on the Noometry Index.
Is Deepseek Coder v2 or Devstral Small 2505 better for coding?
They score almost the same on coding (38.1 vs 38.9); test both on your own repository before choosing.
How many benchmarks do Deepseek Coder v2 and Devstral Small 2505 share?
0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Devstral Small 2505 has 4.