Share your thoughts, 1 month free Claude Pro on usSee more

Hallucination Evaluation on HaloQuest

80.8Score S

Qwen2.5-VL + FINER-Tuning

Updated 1mo ago

Evaluation Results

Method	Links
Qwen2.5-VL + FINER-Tuning 2026.03		80.8	-	-
Qwen2.5-VL 2026.03		74.8	-	-
InternVL-3.5 + FINER-Tuning 2026.03		73.5	-	-
InternVL-3.5 + FINER-Tuning 2026.03		71	-	-
InternVL-3.5 2026.03		65	-	-
LLaVA-1.6 + FINER-Tuning 2026.03		63.5	-	-
OmniLMM + RLAIF-V 2026.03		62.4	-	-
InternVL-3.5 2026.03		62.4	-	-
Qwen2.5-VL-7B+VRGA 2026.03		54.9	73.96	57.8
Qwen2.5-VL-7B 2026.03		50.2	66.67	59.5
Qwen2.5-VL-3B+VRGA 2026.03		48.8	59.03	40.5
Qwen3-VL-30B+VRGA 2026.03		46.5	68.05	74.4
Qwen3-VL-30B 2026.03		45.4	69.2	76.2
Qwen2.5-VL-3B 2026.03		44.5	58.87	60.1
LLaVA-1.6 2026.03		44.2	-	-
Qwen2-VL-7B 2026.03		40.6	53.81	62.2
Qwen2-VL-7B+VRGA 2026.03		40.4	54.47	60.8
OmniLMM 2026.03		39.9	-	-
Qwen2-VL-7B+ICOT 2026.03		36.7	47.85	63.8
Qwen2.5-VL-3B+CCOT 2026.03		-	41.06	-
Qwen2.5-VL-7B+CCOT 2026.03		-	51.08	-
Qwen2-VL-7B+CCOT 2026.03		-	29.3	-