Hallucination-oriented Video Understanding on VidHallucer (test)

62.5Accuracy

Structured Reward Reinforcement Learning

Updated 16d ago

Evaluation Results

Method	Links
Structured Reward Reinforcement Learning 2026.04		62.5
Qwen3-VL-32B 2026.04		62
Structured Reward Reinforcement Learning 2026.04		56.8
Structured Reward Reinforcement Learning 2026.04		55.8
Qwen3-VL-8B 2026.04		55.7
Season 2026.04		55.1
Season 2026.04		54.8
Structured Reward Reinforcement Learning 2026.04		54.8
ArrowRL 2026.04		54.5
Season 2026.04		54.2
GPT-4o 2026.04		53.3
DINO-HEAL 2026.04		53.3
Season 2026.04		53.3
Qwen2.5-VL-7B 2026.04		53.1
TCD 2026.04		52.8
Qwen3-VL-4B 2026.04		51.4
Season 2026.04		49.3
Structured Reward Reinforcement Learning 2026.04		48.5
TCD 2026.04		48.1
DINO-HEAL 2026.04		46.9
LLaVA-OV-7B 2026.04		46.4
Gemini 1.5 Pro 2026.04		37.8