BLIP (ITM)

Reported on 3 benchmarks across 1 task · 1 paper

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

Reasoning3 results

Visual ReasoningonWinoground
Group Score· 2023-06-02
13.3
best: 58.75 (GPT-4V (CoT, pick b/w two options))
Revisiting the Role of Language Priors in Vision-Language Models arXiv:2306.01879
Visual ReasoningonWinoground
Image Score· 2023-06-02
15.8
best: 68.75 (GPT-4V (CoT, pick b/w two options))
Revisiting the Role of Language Priors in Vision-Language Models arXiv:2306.01879
Visual ReasoningonWinoground
Text Score· 2023-06-02
35.8
best: 75.5 (GPT-4o + CA)
Revisiting the Role of Language Priors in Vision-Language Models arXiv:2306.01879