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

Multimodal Reasoning on GeoBench-VLM

35.4Aerial Score

InternVL3-8B + Ours

Updated 4d ago

Evaluation Results

Method	Links
InternVL3-8B + Ours 2026.02		35.4	61.4	42.1	45.7	24.3	48.2
Qwen2.5-VL-7B + Ours 2026.02		26.7	52.3	34	36.7	14.2	39.3
InternVL3-8B 2026.02		26	46.1	38	35.2	20	37.4
LLaVA-1.5-13B + Ours 2026.02		23.6	51.2	17.4	32.5	14.1	34.9
LLaVA-1.5-7B 2026.02		22.4	46.7	27.3	32.1	18.3	34.7
LLaVA-1.5-7B + Ours 2026.02		21.5	49.4	12	34.5	10	33.2
ControlMLLM++ 2026.02		18.1	27.8	16.7	22.8	14.3	22.5
Qwen2.5-VL-7B 2026.02		18	33.5	26.5	27.9	13.3	27.4
Jiang et al. 2026.02		17.4	28.1	15.8	18.9	12.8	21.4
LLaVA-1.5-7B 2026.02		16.5	29.8	14	15.5	12.2	20.9
LLaVA-1.5-13B 2026.02		13.5	37.1	19.5	13.4	13.3	23.7