| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Narration Quality Evaluation | FigTalk-Gold (D1) | Order Match76 | 9 | |
| Grounding | FigTalk-Gold Hard (reference set) | Macro F174.2 | 9 | |
| Grounding | FigTalk-Gold Medium (reference set) | Macro F170.4 | 9 | |
| Grounding Evaluation | FigTalk Extended | Inputs CF Score84 | 8 |