Model card
DeepSeek V4-Pro.
DeepSeek-AIopen-source
§ 02 · Benchmarks
Every benchmark DeepSeek V4-Pro has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | PhysicianBench | Agentic AI · Task agents | pass@1 | 18.7% | #2 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 06 · Sources & freshness
Where these numbers come from.
paper
1
result
1 of 1 rows marked verified.