Model
DeepSeek V4 Pro 0813
DeepSeek · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CritPt | 18.0 | accuracy | N/A | Independent | low | epoch.ai |
| GPQA Diamond | 91.7 | accuracy | N/A | Independent | high | epoch.ai |
| SimpleQA Verified | 52.9 | accuracy | N/A | Independent | high | epoch.ai |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CRUXEval-style | 63.8 | accuracy | N/A | Independent | medium | arxiv.org |
| SciCode | 51.0 | score | N/A | Independent | medium | artificialanalysis.ai |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| EvoRiskBench | 68.2 | success_rate | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract ReasoningReproduced by the community
Loading community runs…