List your company
ResearchFormerly WizWand

Instruction Following on InfoBench (DRFR)

74.19DRFR ScorePolicy-adaptive rubrics
68.355669.870371.38572.8997Jul 5, 2026
Updated 3mo ago

Evaluation results

MethodLinks
Policy-adaptive rubricsPrompt Modification Strategy=No prompt modification, Policy Model=Qwen3-1.7B, Tutor Model=Qwen3-8B, Judge Model=Qwen3-8B2026.0774.19
WildChecklistsPrompt Modification Strategy=No prompt modification, Policy Model=Qwen3-1.7B, Tutor Model=Qwen3-8B, Judge Model=Qwen3-8B2026.0773.8
LLM-as-a-TutorPrompt Modification Strategy=Policy-adaptive prompt modification, Policy Model=Qwen3-1.7B, Tutor Model=Qwen3-8B, Judge Model=Qwen3-8B2026.0773.59
Base rubricsPrompt Modification Strategy=No prompt modification, Policy Model=Qwen3-1.7B, Tutor Model=Qwen3-8B, Judge Model=Qwen3-8B2026.0773.48
EVAPrompt Modification Strategy=Policy-adaptive prompt modification, Policy Model=Qwen3-1.7B, Tutor Model=Qwen3-8B, Judge Model=Qwen3-8B2026.0773.43
Evol-InstructPrompt Modification Strategy=Policy-unaware prompt modification, Policy Model=Qwen3-1.7B, Tutor Model=Qwen3-8B, Judge Model=Qwen3-8B2026.0773.35
Qwen3-1.7BPolicy Model=Qwen3-1.7B, Tutor Model=Qwen3-8B, Judge Model=Qwen3-8B2026.0772.28
DistillationPrompt Modification Strategy=No prompt modification, Policy Model=Qwen3-1.7B, Tutor Model=Qwen3-8B, Judge Model=Qwen3-8B2026.0768.58