Model comparison
Claude 2.1 vs Deepseek Coder v2
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 25.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- The widest gap is in math, where Deepseek Coder v2 leads 34.9 to 10.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Claude 2.1 | Deepseek Coder v2 | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 25.2 | 35.9 |
| Released | 2023-11-21 | 2024-06-17 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Claude 2.1: 26.2 (#327), Deepseek Coder v2: 38.1 (#183)
| Benchmark | Claude 2.1 | Deepseek Coder v2 |
|---|---|---|
| WeirdML | 7.1% | — |
| BigCodeBench Instruct | — | 48.2% |
| LMArena Coding | — | 1251 |
| BigCodeBench Complete | — | 59.7% |
| HumanEval+ | — | 82.3% |
| MBPP+ | — | 75.1% |
Reasoning Deepseek Coder v2 leads
Claude 2.1: 21.4 (#221), Deepseek Coder v2: 23.6 (#176)
| Benchmark | Claude 2.1 | Deepseek Coder v2 |
|---|---|---|
| LMArena Hard Prompts | — | 1207 |
| DTBench | 51% | — |
| Epoch Capabilities Index | 119.27 | — |
| ForecastBench | 54.2 | — |
| WinoGrande | — | 83.7% |
Math Deepseek Coder v2 leads
Claude 2.1: 10.2 (#315), Deepseek Coder v2: 34.9 (#190)
| Benchmark | Claude 2.1 | Deepseek Coder v2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | — | 1241 |
| GSM8K | — | 94.5% |
Knowledge Deepseek Coder v2 leads
Claude 2.1: 15.4 (#292), Deepseek Coder v2: 32.3 (#212)
| Benchmark | Claude 2.1 | Deepseek Coder v2 |
|---|---|---|
| GPQA Diamond | 33% | — |
| LMArena Expert | — | 1181 |
| ARC (AI2) Challenge | — | 64.3% |
| MMLU | 73.5% | — |
Multilingual Not comparable
Claude 2.1: —, Deepseek Coder v2: 36.3 (#240)
| Benchmark | Claude 2.1 | Deepseek Coder v2 |
|---|---|---|
| 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
Claude 2.1: —, Deepseek Coder v2: 61.7 (#242)
| Benchmark | Claude 2.1 | Deepseek Coder v2 |
|---|---|---|
| LMArena Instruction Following | — | 1180 |
Long Context Not comparable
Claude 2.1: —, Deepseek Coder v2: 37.0 (#224)
| Benchmark | Claude 2.1 | Deepseek Coder v2 |
|---|---|---|
| LMArena Longer Query | — | 1219 |
Writing & Preference Not comparable
Claude 2.1: —, Deepseek Coder v2: 38.2 (#253)
| Benchmark | Claude 2.1 | Deepseek Coder v2 |
|---|---|---|
| LMArena Text | — | 1191 |
| LMArena Creative Writing | — | 1120 |
| LMArena Multi-Turn | — | 1177 |
Frequently asked questions
Is Claude 2.1 better than Deepseek Coder v2?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 25.2 on the Noometry Index.
Is Claude 2.1 or Deepseek Coder v2 better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and Deepseek Coder v2 share?
0 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and Deepseek Coder v2 has 24.