| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Reverse Chain-of-Thought Generation | ArenaHard | Score72 | 20 | |
| Creative Writing | ArenaHard creative writing v2.0 | WR Score29 | 13 | |
| Alignment | ArenaHard | pass@195.7 | 7 | |
| Human Preference Alignment | ArenaHard V2 | Avg@3 Score60 | 6 | |
| Chatbot Evaluation | ArenaHard v2 | Hard Prompt Accuracy14 | 4 |