Model comparison
Claude Instant vs DeepSeek-V2 (MoE-236B, May 2024)
Neither Claude Instant nor DeepSeek-V2 (MoE-236B, May 2024) has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 4 shared benchmarks.
DeepSeekSummary
- They share 4 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 Instant | DeepSeek-V2 (MoE-236B, May 2024) | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 29.5 | 40.3 |
| Released | 2023-08-09 | 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 Not comparable
Claude Instant: —, DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139)
| Benchmark | Claude Instant | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| BigCodeBench Instruct | — | 48.9% |
| BigCodeBench Complete | — | 59.4% |
| HumanEval+ | 50.6% | — |
Reasoning Not comparable
Claude Instant: 19.6, DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude Instant | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| Epoch Capabilities Index | 120.28 | 124.77 |
| DTBench | 45.8% | — |
| BIG-Bench Hard | — | 78.8% |
| HellaSwag | — | 87.1% |
| PIQA | — | 83.9% |
| WinoGrande | — | 86.3% |
Math Not comparable
Claude Instant: —, DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude Instant | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| GSM8K | 86.7% | — |
Knowledge Not comparable
Claude Instant: —, DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | Claude Instant | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| ARC (AI2) Challenge | 86.3% | 92.2% |
| MMLU | 73.4% | 78.4% |
| TriviaQA | 78.9% | 80% |
Frequently asked questions
Is Claude Instant better than DeepSeek-V2 (MoE-236B, May 2024)?
Neither Claude Instant nor DeepSeek-V2 (MoE-236B, May 2024) has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do Claude Instant and DeepSeek-V2 (MoE-236B, May 2024) share?
4 benchmarks have published results for both models. Claude Instant has 7 scored results on Noometry and DeepSeek-V2 (MoE-236B, May 2024) has 10.