2 vs 0 benchmarks won
Anthropic Claude Opus 4.6 | DeepSeek DeepSeek-V4-Pro | |
|---|---|---|
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Feb 5 2026 | Apr 24 2026 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 91.3% | 90.1% |
Software engineering SWE-Bench Verified | 80.8% | — |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Claude Opus 4.6 shipped 78 days before DeepSeek-V4-Pro | |
Claude Opus 4.6 leads DeepSeek-V4-Pro on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude Opus 4.6 shipped 78 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 Opus 4.6 is proprietary.
On GPQA Diamond, Claude Opus 4.6 scores 91.3%, 1.2 points above DeepSeek-V4-Pro at 90.1%.