IDEFICS 80B

Reported on 3 benchmarks across 1 task

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
8
best: 58.75 (GPT-4V (CoT, pick b/w two options))
Visual ReasoningonWinoground
Image Score
22.5
best: 68.75 (GPT-4V (CoT, pick b/w two options))
Visual ReasoningonWinoground
Text Score
18.75
best: 75.5 (GPT-4o + CA)