Model comparison
Claude 2.1 vs DeepSeek-V2 (MoE-236B, May 2024)
Claude 2.1 has enough public results to be ranked (#345); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
DeepSeekSummary
- They share 2 benchmarks with published results for both. Claude 2.1 scores higher in 0 categories and DeepSeek-V2 (MoE-236B, May 2024) in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 26.2.
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.
Side by side
| Claude 2.1 | DeepSeek-V2 (MoE-236B, May 2024) | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 25.2 | 40.3 |
| Released | 2023-11-21 | 2024-05-07 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
Claude 2.1: 26.2 (#327), DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139)
| Benchmark | Claude 2.1 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| WeirdML | 7.1% | — |
| BigCodeBench Instruct | — | 48.9% |
| BigCodeBench Complete | — | 59.4% |
Reasoning Not comparable
Claude 2.1: 21.4 (#221), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude 2.1 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| Epoch Capabilities Index | 119.27 | 124.77 |
| DTBench | 51% | — |
| BIG-Bench Hard | — | 78.8% |
| ForecastBench | 54.2 | — |
| HellaSwag | — | 87.1% |
| PIQA | — | 83.9% |
| WinoGrande | — | 86.3% |
Math Not comparable
Claude 2.1: 10.2 (#315), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude 2.1 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |
Knowledge Not comparable
Claude 2.1: 15.4 (#292), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude 2.1 | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| MMLU | 73.5% | 78.4% |
| GPQA Diamond | 33% | — |
| ARC (AI2) Challenge | — | 92.2% |
| TriviaQA | — | 80% |
Frequently asked questions
Is Claude 2.1 better than DeepSeek-V2 (MoE-236B, May 2024)?
Claude 2.1 has enough public results to be ranked (#345); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is Claude 2.1 or DeepSeek-V2 (MoE-236B, May 2024) better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 26.2 in the Noometry coding category.
How many benchmarks do Claude 2.1 and DeepSeek-V2 (MoE-236B, May 2024) share?
2 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and DeepSeek-V2 (MoE-236B, May 2024) has 10.