Next Query Prediction on NQP Share Bench
48.77Judge ScoreOnePred
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| OnePredModel Regime=Gemini-3.1-Pro, History Context Strategy=Ours2026.05 | 48.77 | 49.66 | |
| Gemini-3.1-ProModel Regime=Gemini-3.1-Pro, History Context Strategy=Full-history2026.05 | 46.3 | 46.13 | |
| OnePredModel Regime=RL-trained Qwen, History Context Strategy=Ours2026.05 | 43.84 | 44.96 | |
| Gemini-3.1-ProModel Regime=Gemini-3.1-Pro, History Context Strategy=Current-turn2026.05 | 42.78 | 43.33 | |
| RL-trained QwenModel Regime=RL-trained Qwen, History Context Strategy=Full-history2026.05 | 42.16 | 42.53 | |
| RL-trained QwenModel Regime=RL-trained Qwen, History Context Strategy=Current-turn2026.05 | 40.5 | 40.22 | |
| OnePredModel Regime=Base Qwen, History Context Strategy=Ours2026.05 | 37.84 | 37.62 | |
| Base QwenModel Regime=Base Qwen, History Context Strategy=Full-history2026.05 | 35.69 | 36.3 | |
| Base QwenModel Regime=Base Qwen, History Context Strategy=Current-turn2026.05 | 35.02 | 35.86 |