{"task":"Multimodal Reasoning","dataset":"AlgoPuzzleVQA","metric_names":["Acc"],"rows":[{"id":141453,"task":"Multimodal Reasoning","parent_task":null,"dataset":"AlgoPuzzleVQA","model_name":"GPT-4","metrics":{"Acc":"30.3"},"paper_url":"https://arxiv.org/abs/2403.03864v3","paper_title":"Are Language Models Puzzle Prodigies? Algorithmic Puzzles Unveil Serious Challenges in Multimodal Reasoning","paper_date":"2024-03-06","code_links":[{"title":"declare-lab/puzzle-reasoning","url":"https://github.com/declare-lab/puzzle-reasoning"},{"title":"declare-lab/llm-puzzletest","url":"https://github.com/declare-lab/llm-puzzletest"}],"metrics_order":"[\"Acc\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]}]}