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

Hallucination Assessment on RSHalluEval 1.0 (test)

0.9792HF Information Accuracy

Qwen2-VL

Updated 3d ago

Evaluation Results

Method	Links
Qwen2-VL 2026.02		0.9792	0.9563	0.9022	0.8318	0.7594	0.8744
LHRS-Bot-Nova 2026.02		0.9167	0.8938	0.7532	0.6975	0.4717	0.7286
VHM 2026.02		0.9167	0.9438	0.8137	0.659	0.4387	0.7425
VHM 2026.02		0.913	0.8125	0.7521	0.4853	0.8	0.6833
VHM 2026.02		0.8958	0.7	0.752	0.3611	0.4906	0.6055
LLaVA-1.5 2026.02		0.8542	0.9125	0.7858	0.6034	0.4623	0.7084
GeoChat 2026.02		0.8056	0.8375	0.7404	0.6296	0.4434	0.6861
GeoChat 2026.02		0.75	0.5455	0.4167	0.375	0.4833	0.4417
LHRS-Bot 2026.02		0.7292	0.725	0.5995	0.4753	0.4198	0.5601
LHRS-Bot-Nova 2026.02		0.7273	0.8696	0.7946	0.4853	0.5417	0.67
mPLUG-Owl3 2026.02		0.6806	0.925	0.8428	0.716	0.4811	0.7593
LHRS-Bot-Nova 2026.02		0.6736	0.6625	0.7893	0.4475	0.4528	0.6263
Qwen2-VL 2026.02		0.6181	0.7813	0.8242	0.5864	0.5802	0.7044
Qwen2-VL 2026.02		0.6111	0.7941	0.7428	0.5745	0.6818	0.6783
GeoChat 2026.02		0.5625	0.3188	0.4994	0.3025	0.2877	0.4043
LLaVA-1.5 2026.02		0.375	0.8462	0.5597	0.4857	0.5357	0.5317
LLaVA-1.5 2026.02		0.3333	0.575	0.6601	0.3519	0.3679	0.5007
mPLUG-Owl3 2026.02		0.2778	0.775	0.8231	0.4846	0.5566	0.6441
LHRS-Bot 2026.02		0.2431	0.3063	0.4878	0.2731	0.3255	0.3702
mPLUG-Owl3 2026.02		0.1667	0.82	0.8661	0.517	0.75	0.69
LHRS-Bot 2026.02		0.1667	0.4211	0.4346	0.2898	0.4242	0.3633