DeepSeek V4 Pro 0813 — Benchmarks
Benchmark scores for DeepSeek V4 Pro 0813 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #15 of 123 open modelscomposite 67/100 across 10 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SciCode | 49.2% | #8 / 50 | #63 / 155 |
| LiveBench Coding | 77.2 | #6 / 16 | #29 / 54 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SimpleQA | 52.9% | #1 / 15 | #16 / 78 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 98.6% | #1 / 74 | #12 / 270 |
| LiveBench Math | 95.1 | #1 / 16 | #8 / 54 |
| ProofBench | 50.0% | #3 / 21 | #18 / 64 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 91.7% | #3 / 83 | #22 / 291 |
| ARC-AGI | 90.5% | #2 / 16 | #47 / 200 |
| LiveBench Reasoning | 85.8 | #4 / 16 | #25 / 54 |
| CritPt | 18.0% | #4 / 50 | #41 / 167 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.