Hallucination-oriented Video Understanding on EventHallusion (test)

91.9Accuracy

GPT-4o

Updated 16d ago

Evaluation Results

Method	Links
GPT-4o 2026.04		91.9
Gemini 1.5 Pro 2026.04		80.4
Structured Reward Reinforcement Learning 2026.04		78
Qwen3-VL-32B 2026.04		77
Structured Reward Reinforcement Learning 2026.04		73.4
Structured Reward Reinforcement Learning 2026.04		72
Season 2026.04		71.6
Season 2026.04		71.6
Season 2026.04		69.2
ArrowRL 2026.04		69
TCD 2026.04		68.5
Qwen3-VL-4B 2026.04		68.4
Season 2026.04		67.9
Qwen3-VL-8B 2026.04		66.8
Season 2026.04		66
Structured Reward Reinforcement Learning 2026.04		65.8
TCD 2026.04		64.8
Structured Reward Reinforcement Learning 2026.04		64.2
DINO-HEAL 2026.04		63.6
Qwen2.5-VL-7B 2026.04		63.3
LLaVA-OV-7B 2026.04		60.2
DINO-HEAL 2026.04		60.2