| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| DEMO | Qwen2-72B-Instruct | Goal Achievement8.447 | 20 | 1mo ago | |
| DEMO Average | Llama3.1-8B-Instruct w/ AMPO | Goal Achievement Score8.14 | 12 | 1mo ago | |
| DEMO Non-Collaboration set | Llama3.1-8B-Instruct w/ AMPO | Goal Achievement Score8.03 | 12 | 1mo ago | |
| DEMO Collaboration set | Llama3.1-8B-Instruct w/ AMPO | Goal Achievement Score8.65 | 12 | 1mo ago |