List your company

Segment-level mistake detection on CaptainCook4D (Average)

72.3EDAAMNAR
68.86869.75970.6571.541Jun 19, 2026

Evaluation results

MethodLinks
AMNAREvaluation Protocol=Fully supervised2026.0672.3—
AEMEvaluation Protocol=Fully supervised2026.0671.9—
EgoPEDEvaluation Protocol=Fully supervised2026.0669.8—
ZeProM (Q-M)Evaluation Protocol=Zero-shot, Backbone=Qwen3.5-35B-A3B2026.0669.614
ZeProM (Q-L)Evaluation Protocol=Zero-shot, Backbone=Qwen3.5-397B-A17B-GPTQ-Int42026.066917.9