2 vs 1 benchmarks won
Anthropic Claude Sonnet 4.5 | DeepSeek DeepSeek-V4-Pro | |
|---|---|---|
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Sep 29 2025 | Apr 24 2026 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 83.4% | 90.1% |
Software engineering SWE-Bench Verified | 77.2% | — |
Multimodal understanding MMMU | 68% | — |
| Timeline | ||
| Release gap | Claude Sonnet 4.5 shipped 207 days before DeepSeek-V4-Pro | |
Claude Sonnet 4.5 leads DeepSeek-V4-Pro on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude Sonnet 4.5 shipped 207 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Pro is an open-source / open-weight model; Claude Sonnet 4.5 is proprietary.
On GPQA Diamond, DeepSeek-V4-Pro scores 90.1%, 6.7 points above Claude Sonnet 4.5 at 83.4%.