HUMANUAL
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Evaluation Simulation | Humanual Opinion | Primary Metric46.2 | 9 | |
| Roleplay Simulation | Humanual Politics | Primary Metric43.5 | 9 | |
| Roleplay Simulation | Humanual News | Primary Metric42.7 | 9 | |
| Response Alignment | HUMANUAL (test) | Alignment Score (Chat)6.08 | 8 | |
| User Simulation | HUMANUAL (test) | News Score40.58 | 3 |
Showing 5 of 5 rows