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.
Overall rank: #3 of 73 open modelscomposite 74.3/100 across 7 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| LiveBench Coding | 70.0 | #6 / 8 | #32 / 37 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SimpleQA | 57.0% | #1 / 11 | #12 / 65 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 96.7% | #1 / 34 | #11 / 155 |
| LiveBench Math | 90.7 | #1 / 8 | #15 / 37 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SimpleBench | 61.2% | #1 / 19 | #22 / 90 |
| GPQA Diamond | 89.6% | #2 / 46 | #23 / 182 |
| LiveBench Reasoning | 82.7 | #2 / 8 | #23 / 37 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.