ChatCaptioner + ChatGPT

Reported on 1 benchmark across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Reasoning1 result

Visual ReasoningonBongard-OpenWorld
2-Class Accuracy· 2023-10-16
49.3
best: 93.6 (Gemini-2.0 + CA)
Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World arXiv:2310.10207