List your company

Next Query Prediction on NQP Wild Bench

50.72Judge ScoreOnePred
35.504839.454943.40547.3551May 22, 2026

Evaluation results

MethodLinks
OnePredModel Regime=Gemini-3.1-Pro, History Context Strategy=Ours2026.0550.7251.14
Gemini-3.1-ProModel Regime=Gemini-3.1-Pro, History Context Strategy=Full-history2026.0548.8149.86
OnePredModel Regime=RL-trained Qwen, History Context Strategy=Ours2026.054647.27
Gemini-3.1-ProModel Regime=Gemini-3.1-Pro, History Context Strategy=Current-turn2026.0545.5345.31
RL-trained QwenModel Regime=RL-trained Qwen, History Context Strategy=Full-history2026.0544.3544.97
RL-trained QwenModel Regime=RL-trained Qwen, History Context Strategy=Current-turn2026.0544.0244.2
OnePredModel Regime=Base Qwen, History Context Strategy=Ours2026.0539.5740.42
Base QwenModel Regime=Base Qwen, History Context Strategy=Full-history2026.0538.239.16
Base QwenModel Regime=Base Qwen, History Context Strategy=Current-turn2026.0536.0936.42