DeepSeek V4 Pro — Benchmarks
Benchmark scores for DeepSeek V4 Pro aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Coding
| Benchmark | Score | Rank |
|---|---|---|
| LiveBench Coding | 70.0 | #8 / 17 |
Math
| Benchmark | Score | Rank |
|---|---|---|
| LiveBench Math | 90.7 | #1 / 17 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| LiveBench Reasoning | 82.7 | #1 / 17 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.