Model

InternVL3.5-14B

Shanghai AI Lab · open weights

Multimodal

Benchmark	Score	Metric	Harness	Source	Confidence	Link
4MT-VLM	31.0	accuracy	N/A	Independent	medium	arxiv.org
DataVista	47.4	accuracy	N/A	Independent	medium	arxiv.org
SpaceConflict	60.5	accuracy	N/A	Independent	medium	arxiv.org