| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Two-Player Zero-Sum Game Solving | Goofspiel 13 cards | Estimated PE73.9 | 112 | |
| Game Playing | Goofspiel Standard Benchmarks (test) | Exploitability0.007 | 8 | |
| Game Playing | Control Goofspiel (test) | Exploitability0.105 | 4 | |
| Multi-agent Game Playing | Goofspiel 8 point cards | Metric- | 0 |