Evaluating Multimodal LLMs Using the Google IO 2024 Puzzle (hiresynth.ai)

GPT-4V, Claude 3 Opus and Gemini Ultra go head to head in solving GoogleIO Puzzle 2024

Surprising to see these models stumbling on what at first glance seems like a simple task, it would be interesting to see how the non-vision models fare if you convert the problems to ascii art