List your company

Next Query Prediction on NQP-Bench Priv

44.22Judge ScoreOnePred
28.30832.43936.5740.701May 22, 2026

Evaluation results

MethodLinks
OnePredModel Regime=Gemini-3.1-Pro, History Context Strategy=Ours2026.0544.2244.85
OnePredModel Regime=RL-trained Qwen, History Context Strategy=Ours2026.0542.1542.72
Gemini-3.1-ProModel Regime=Gemini-3.1-Pro, History Context Strategy=Current-turn2026.0541.1842.1
Gemini-3.1-ProModel Regime=Gemini-3.1-Pro, History Context Strategy=Full-history2026.0540.8141.15
RL-trained QwenModel Regime=RL-trained Qwen, History Context Strategy=Full-history2026.0540.7940.64
RL-trained QwenModel Regime=RL-trained Qwen, History Context Strategy=Current-turn2026.0538.1738.63
OnePredModel Regime=Base Qwen, History Context Strategy=Ours2026.0533.4633.18
Base QwenModel Regime=Base Qwen, History Context Strategy=Full-history2026.0531.3731.85
Base QwenModel Regime=Base Qwen, History Context Strategy=Current-turn2026.0528.9230.07