| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Blackjack | Blackjack 900 games | Win Rate4,090 | 24 | |
| VLM Reasoning | BlackJack (In-Distribution) | Success Rate43.8 | 15 | |
| Blackjack Decision Policy Evaluation | Blackjack (Out-of-Sample) | Hit-Rate46.3 | 5 | |
| Blackjack Decision Policy Evaluation | Blackjack (In-Sample) | Hit-Rate44.3 | 5 | |
| Card Games | BlackJack | SR42.6 | 3 |