Online Prediction on Online Stratified length T = 100
9.3Mean RegretDeepSeek-V3
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepSeek-V3Protocol=history-free note (+note)2026.05 | 9.3 | |
| DeepSeek-V3Protocol=multi-turn no-note (-note)2026.05 | 13.9 | |
| Qwen-3-14BProtocol=multi-turn no-note (-note)2026.05 | 17.8 | |
| Qwen-3-14BProtocol=history-free note (+note)2026.05 | 20.7 |