Model comparison
Claude 2 vs Deepseek Coder v2
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 25.0 on the Noometry Index.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. Claude 2 scores higher in 0 categories and Deepseek Coder v2 in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Deepseek Coder v2 leads 34.9 to 9.3.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Claude 2 | Deepseek Coder v2 | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 25.0 | 35.9 |
| Released | 2023-07-11 | 2024-06-17 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 8 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, Deepseek Coder v2: 38.1 (#183)
| Benchmark | Claude 2 | Deepseek Coder v2 |
|---|---|---|
| HumanEval+ | 61.6% | 82.3% |
| BigCodeBench Instruct | — | 48.2% |
| LMArena Coding | — | 1251 |
| BigCodeBench Complete | — | 59.7% |
| MBPP+ | — | 75.1% |
Reasoning Deepseek Coder v2 leads
Claude 2: 21.7 (#216), Deepseek Coder v2: 23.6 (#176)
| Benchmark | Claude 2 | Deepseek Coder v2 |
|---|---|---|
| LMArena Hard Prompts | — | 1207 |
| DTBench | 51.9% | — |
| Epoch Capabilities Index | 120.13 | — |
| WinoGrande | — | 83.7% |
Math Deepseek Coder v2 leads
Claude 2: 9.3 (#320), Deepseek Coder v2: 34.9 (#190)
| Benchmark | Claude 2 | Deepseek Coder v2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| LMArena Math | — | 1241 |
| MATH Level 5 | 11.7% | — |
| GSM8K | — | 94.5% |
Knowledge Deepseek Coder v2 leads
Claude 2: 16.9 (#287), Deepseek Coder v2: 32.3 (#212)
| Benchmark | Claude 2 | Deepseek Coder v2 |
|---|---|---|
| GPQA Diamond | 34.7% | — |
| LMArena Expert | — | 1181 |
| ARC (AI2) Challenge | — | 64.3% |
| MMLU | 78.5% | — |
| TriviaQA | 87.5% | — |
Multilingual Not comparable
Claude 2: —, Deepseek Coder v2: 36.3 (#240)
| Benchmark | Claude 2 | 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: —, Deepseek Coder v2: 61.7 (#242)
| Benchmark | Claude 2 | Deepseek Coder v2 |
|---|---|---|
| LMArena Instruction Following | — | 1180 |
Long Context Not comparable
Claude 2: —, Deepseek Coder v2: 37.0 (#224)
| Benchmark | Claude 2 | Deepseek Coder v2 |
|---|---|---|
| LMArena Longer Query | — | 1219 |
Writing & Preference Not comparable
Claude 2: —, Deepseek Coder v2: 38.2 (#253)
| Benchmark | Claude 2 | Deepseek Coder v2 |
|---|---|---|
| LMArena Text | — | 1191 |
| LMArena Creative Writing | — | 1120 |
| LMArena Multi-Turn | — | 1177 |
Frequently asked questions
Is Claude 2 better than Deepseek Coder v2?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 25.0 on the Noometry Index.
How many benchmarks do Claude 2 and Deepseek Coder v2 share?
1 benchmark has published results for both models. Claude 2 has 8 scored results on Noometry and Deepseek Coder v2 has 24.