Panoramic Visual Question Answering on PanoVQA (test) benchmark leaderboard · SOTA2 Research

Panoramic Visual Question Answering on PanoVQA (test)

34.79Accuracy (N1)PanoLM-7B

Evaluation Results

Method	Links
PanoLM-7B2026.03		34.79	33.54	28.18	28.54	18.62	50.21	60.09	23.65	42.92	75.72	76.74	72.75	45.48
Qwen2.5-VL-7B2026.03		33.52	34.22	27.57	27.66	22.66	50	58.26	23.21	42.08	74.07	74.9	74.34	45.21
Gemini-2.5-Flash-Lite2026.03		18.83	23.61	25.21	19.07	11.21	36.81	45.25	14.08	31.72	32.62	41.79	68.64	30.74
Qwen2.5-VL-32B-Ins.2026.03		16.51	20.88	26.34	17.51	9.85	46.23	54.61	15.45	35.56	54.11	55.14	74.55	35.56
InternVL3-8B-Ins.2026.03		15.06	22.79	23.99	16.14	9.32	45.91	53.38	15.06	36.06	57.87	52.98	65.17	34.48
Qwen2.5-VL-7B-Ins.2026.03		13.65	18.53	22.08	14.72	15.13	35.89	44.68	12.86	30.97	48.86	36.93	62.9	29.77
InternVL2-8B2026.03		12.79	22.55	24.17	15.59	9.17	43.35	50.8	15.11	33.88	49.73	46.71	40.51	30.36
LLaVA-OneVision-7B2026.03		12.54	19.61	19.83	14.49	11.97	40.66	43.25	12.05	25.88	47.09	34.75	43	27.09
DeepSeek-VL2-Small2026.03		12.5	19.45	15.66	13.71	12.46	38.69	40.64	13.77	33.48	52.01	45.83	10.04	25.69
GLM-4-9B2026.03		11.73	15.6	19.36	13.34	11.93	44.74	53.44	10.93	31.42	46.64	43.29	52.36	29.57
LLaVA-NEXT-7B2026.03		11.19	17.15	15.06	12.13	10.54	40.47	46.91	8.93	20.66	36.73	23.33	18.57	21.81
Chameleon-7B2026.03		9.87	18.04	12.6	10.62	6.98	33.04	38.96	8.71	23.65	35.01	30.76	11.69	19.99
Grok-3-Mini2026.03		3.38	6.88	11.61	8.42	5.37	34.23	34.58	7.91	19.3	35	26.15	68.05	21.74