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

Spatial Relation Understanding on SO-Bench

64.26IS-DoA

SO-30B

Updated 1mo ago

Evaluation Results

Method	Links
SO-30B 2026.06		64.26	53.6	53.15	65.46	64.86	88.09
SO-7B(MIX) 2026.06		64.17	59.91	51.05	61.26	64.26	82.96
BAT 2026.06		62.67	58.56	52.85	52.25	52.85	72.9
SO-7B-iv 2026.06		56.37	54.35	49.85	47.75	60.06	82.55
SO-7B-neuiv 2026.06		55.77	54.05	62.16	52.25	61.86	81.25
SO-7B-zs 2026.06		51.72	40.69	47.15	49.55	50.15	53.58
SO-7B-so 2026.06		41.83	39.49	51.65	45.05	48.65	40.25
Kimi-Audio 2026.06		41.08	28.53	42.64	50.75	58.56	54.21
Gemini-3-pro 2026.06		36.28	28.98	38.64	53.49	68.18	45
Qwen-2.5-Omni 2026.06		34.63	24.77	49.55	50.45	59.76	37.78
Gemini-2.5-pro 2026.06		34.33	21.47	50.75	49.25	58.86	33.06
Audio Flamingo 3 2026.06		32.83	16.37	52.55	51.35	62.42	51.33
Gemini-2.5-flash 2026.06		29.39	13.21	42.34	49.25	55.56	43.33
GPT-audio 2026.06		26.87	11.94	64.52	45.16	46.88	5
Phi-4-MM 2026.06		22.34	22.22	44.74	55.86	64.56	49.49
Qwen-3-Omni 2026.06		21.77	39.58	49.21	51.61	46.03	35.11