List your company

Multi-Hop Search

59Overall Avg@4 (Least-Time)Teacher
35.163241.351647.5453.7284Jul 7, 2026

Evaluation results

MethodLinks
TeacherStudent=Qwen3.5-2B, Teacher=Qwen3.5-9B-GRPO2026.075959——
TurnOPDStudent=Qwen3.5-2B, Teacher=Qwen3.5-9B-GRPO2026.0747.2447.242.941.51
Vanilla OPDStudent=Qwen3.5-2B, Teacher=Qwen3.5-9B-GRPO2026.0745.7747.824.451
TCOD-F2BStudent=Qwen3.5-2B, Teacher=Qwen3.5-9B-GRPO2026.0745.6447.773.81.17
Zero-ShotStudent=Qwen3.5-2B, Teacher=Qwen3.5-9B-GRPO2026.0736.0836.08——