List your company

Object Hallucination Detection on nocaps-FOIL (Near-Domain)

92.6APEXPERT
65.66472.65779.6586.643May 20, 2026

Evaluation results

MethodLinks
EXPERTMethod Category=LLM-based2026.0592.69398.5
VQAScoreMethod Category=LLM-based, Backbone=CLIP-FlanT5-XXL2026.0588.889.495.1
FLEURMethod Category=LLM-based2026.0588.49097.9
BEiTScore-L/14Method Category=Encoder-based, Backbone=BEiT-L/142026.0587.588.998.3
BEiTScore-B/32Method Category=Encoder-based, Backbone=BEiT-B/322026.0586.186.898.6
PAC-S++Method Category=Encoder-based, Backbone=ViT-L2026.057780.795.1
LongCLIP-SMethod Category=Encoder-based, Backbone=ViT-L2026.0576.978.896.3
PAC-SMethod Category=Encoder-based, Backbone=ViT-L2026.0574.277.892.5
PAC-SMethod Category=Encoder-based, Backbone=ViT-B2026.0573.276.990.7
PAC-S++Method Category=Encoder-based, Backbone=ViT-B2026.0573.27792.7
LongCLIP-SMethod Category=Encoder-based, Backbone=ViT-B2026.0572.975.994.9
BEiTScore-L/14 w/o Stage 1Method Category=Encoder-based, Backbone=BEiT-L/14, Training Stage=w/o Stage 12026.0571.974.496.2
SPECSMethod Category=Encoder-based2026.0571.775.197.3
CLIP-SMethod Category=Encoder-based, Backbone=ViT-L2026.0570.873.990.3
BEiTScore-B/32 w/o Stage 1Method Category=Encoder-based, Backbone=BEiT-B/32, Training Stage=w/o Stage 12026.0569.872.694.2
CLIP-SMethod Category=Encoder-based, Backbone=ViT-B2026.0568.771.887
ALOHaMethod Category=LLM-based2026.0566.7——
GPT4o (API)Method Category=LLM-based2026.05——93.6