GPT-5-pro
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text Detectability | GPT-5-pro Experiment 2 averaged over n ∈ {3, ..., 10} 2025-10-06 | BERT Score99 | 5 | |
| Agreement analysis of causal graph metrics | GPT-5-pro Experiment 3 2025-10-06 | Pearson Correlation Coefficient0.929 | 4 |
Showing 2 of 2 rows