| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Theory of Mind Reasoning | FanToM | 1st-Order Accuracy96.13 | 16 | |
| Theory of Mind | FANToM | Accuracy95 | 14 | |
| Cognitive Simulation | Fantom | Primary Metric (Fantom)93 | 9 | |
| Promoter DNA sequence generation | FANTOM5 human promoter sequences (test) | MSE0.027 | 8 | |
| Theory of Mind Question Answering | FanToM | Accuracy91.7 | 4 | |
| Theory-of-Mind Reasoning | FANToM (400-question stratified split) | BeliefQA Accuracy67.5 | 3 |