Claude 3.7 Sonnet vs DeepSeek Chat (R1-based)
Anthropic Claude 3.7 Sonnet | DeepSeek DeepSeek Chat (R1-based) | |
|---|---|---|
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Feb 24 2025 | Jan 20 2025 |
| Access | Proprietary | Open Weight |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 49% | — |
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 62.3% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 68% | — |
| Timeline | ||
| Release gap | DeepSeek Chat (R1-based) shipped 35 days before Claude 3.7 Sonnet | |
Which is better: Claude 3.7 Sonnet or DeepSeek Chat (R1-based)?
Claude 3.7 Sonnet and DeepSeek Chat (R1-based) don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek Chat (R1-based) shipped 35 days before Claude 3.7 Sonnet, so benchmark comparisons should account for the intervening progress.
Claude 3.7 Sonnet is proprietary, while DeepSeek Chat (R1-based) is open weight.
Direct benchmark comparisons are unavailable — Claude 3.7 Sonnet and DeepSeek Chat (R1-based) don't publish scores on any of the same benchmarks.
Frequently asked questions
Claude 3.7 Sonnet was released by Anthropic on Feb 24 2025.
DeepSeek Chat (R1-based) was released by DeepSeek on Jan 20 2025.
Claude 3.7 Sonnet is a proprietary model released by Anthropic. DeepSeek Chat (R1-based) is an open weight model released by DeepSeek.