| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Forecasting | FutureX | Brier Score0.187 | 16 | |
| Web-retrieval Task Completion | FutureX | Pass@149.5 | 14 | |
| Agent Evaluation | FutureX May W2, 56 events | Rank5 | 6 | |
| Future Prediction | FUTUREX March 2026 Week 3 slice | L1 Score71.43 | 6 | |
| Agent Evaluation | FutureX 48 events May W1 | Rank1 | 3 | |
| Agent Evaluation | FutureX Apr. W4 48 events | Rank1 | 3 | |
| Agent Evaluation | FutureX 56 events Apr. W3 | Rank2 | 3 |