Model comparison
Claude 2 vs DeepSeek-V2 (MoE-236B, May 2024)
Claude 2 has enough public results to be ranked (#346); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
DeepSeekSummary
- They share 3 benchmarks with published results for both.
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.
Side by side
| Claude 2 | DeepSeek-V2 (MoE-236B, May 2024) | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 25.0 | 40.3 |
| Released | 2023-07-11 | 2024-05-07 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 8 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 2: —, DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139)
| Benchmark | Claude 2 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| BigCodeBench Instruct | — | 48.9% |
| BigCodeBench Complete | — | 59.4% |
| HumanEval+ | 61.6% | — |
Reasoning Not comparable
Claude 2: 21.7 (#216), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude 2 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| Epoch Capabilities Index | 120.13 | 124.77 |
| DTBench | 51.9% | — |
| BIG-Bench Hard | — | 78.8% |
| HellaSwag | — | 87.1% |
| PIQA | — | 83.9% |
| WinoGrande | — | 86.3% |
Math Not comparable
Claude 2: 9.3 (#320), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude 2 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 11.7% | — |
Knowledge Not comparable
Claude 2: 16.9 (#287), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude 2 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| MMLU | 78.5% | 78.4% |
| TriviaQA | 87.5% | 80% |
| GPQA Diamond | 34.7% | — |
| ARC (AI2) Challenge | — | 92.2% |
Frequently asked questions
Is Claude 2 better than DeepSeek-V2 (MoE-236B, May 2024)?
Claude 2 has enough public results to be ranked (#346); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
How many benchmarks do Claude 2 and DeepSeek-V2 (MoE-236B, May 2024) share?
3 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and DeepSeek-V2 (MoE-236B, May 2024) has 10.