List your company

Next Query Prediction on NQP-Bench Average

47.9Judge ScoreOnePred
32.757636.688840.6244.5512May 22, 2026

Evaluation results

MethodLinks
OnePredModel Regime=Gemini-3.1-Pro, History Context Strategy=Ours2026.0547.948.55
Gemini-3.1-ProModel Regime=Gemini-3.1-Pro, History Context Strategy=Full-history2026.0545.3145.71
OnePredModel Regime=RL-trained Qwen, History Context Strategy=Ours2026.054444.98
Gemini-3.1-ProModel Regime=Gemini-3.1-Pro, History Context Strategy=Current-turn2026.0543.1643.58
RL-trained QwenModel Regime=RL-trained Qwen, History Context Strategy=Full-history2026.0542.4342.71
RL-trained QwenModel Regime=RL-trained Qwen, History Context Strategy=Current-turn2026.0540.941.02
OnePredModel Regime=Base Qwen, History Context Strategy=Ours2026.0536.9637.07
Base QwenModel Regime=Base Qwen, History Context Strategy=Full-history2026.0535.0935.77
Base QwenModel Regime=Base Qwen, History Context Strategy=Current-turn2026.0533.3434.12