{"data":[{"revision":1,"title":"When T2I-CompBench++ uses multimodal LLMs (GPT-4V, ShareGPT4V, MiniGPT-4) as the judge, how do they compare with specialised metrics, how stable are they, and what failure modes does the paper report?","status":"active","change_note":"created","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import"},"created_at":"2026-10-23T21:42:38.785Z"}]}