List your company

Object Hallucination Detection on nocaps-FOIL (Overall)

91.1APEXPERT
68.42874.31480.286.086May 20, 2026

Evaluation results

MethodLinks
EXPERTMethod Category=LLM-based2026.0591.192.298.5
VQAScoreMethod Category=LLM-based, Backbone=CLIP-FlanT5-XXL2026.058889.195.2
BEiTScore-L/14Method Category=Encoder-based, Backbone=BEiT-L/142026.0587.388.898.2
FLEURMethod Category=LLM-based2026.0586.888.797.2
BEiTScore-B/32Method Category=Encoder-based, Backbone=BEiT-B/322026.0585.586.398.1
LongCLIP-SMethod Category=Encoder-based, Backbone=ViT-L2026.0578.28096.8
PAC-S++Method Category=Encoder-based, Backbone=ViT-L2026.0577.58195.7
PAC-SMethod Category=Encoder-based, Backbone=ViT-B2026.0574.778.291.8
PAC-SMethod Category=Encoder-based, Backbone=ViT-L2026.0574.778.392.7
PAC-S++Method Category=Encoder-based, Backbone=ViT-B2026.0574.277.992.8
LongCLIP-SMethod Category=Encoder-based, Backbone=ViT-B2026.0574.177.195
BEiTScore-L/14 w/o Stage 1Method Category=Encoder-based, Backbone=BEiT-L/14, Training Stage=w/o Stage 12026.0572.575.595.8
CLIP-SMethod Category=Encoder-based, Backbone=ViT-L2026.0571.775.190.7
SPECSMethod Category=Encoder-based2026.0571.174.397
BEiTScore-B/32 w/o Stage 1Method Category=Encoder-based, Backbone=BEiT-B/32, Training Stage=w/o Stage 12026.0570.473.194.1
CLIP-SMethod Category=Encoder-based, Backbone=ViT-B2026.057073.787.5
ALOHaMethod Category=LLM-based2026.0569.3——
GPT4o (API)Method Category=LLM-based2026.05——92.9