Our new X account is live! Follow @wizwand_team for updates

Hallucination Evaluation on HalBench

76.7Score

Qwen3-VL-8B-Thinking + DiG

Updated 4d ago

Evaluation Results

Method	Links
Qwen3-VL-8B-Thinking + DiG 2025.12		76.7
Qwen3-VL-4B-Thinking + DiG 2025.12		73.8
Qwen3-VL-8B-Thinking 2025.12		73.3
Qwen3-VL-4B-Thinking 2025.12		70.1
InternVL2.5-78B 2025.12		57.1
Qwen2.5-VL-72B 2025.12		55.2
Qwen2.5-VL-7B 2025.12		50.1