{"id":"2406.09891","title":"Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming","url":"https://codeofpaper.com/paper/2406.09891","arxiv_url":"https://arxiv.org/abs/2406.09891","published":"2024-06-01","code":"community","best":{"full_name":"machine-teaching-group/neurips2024-benchmark-ct","url":"https://github.com/machine-teaching-group/neurips2024-benchmark-ct","tier":"high_confidence_community","stars":0,"license":"MIT","framework":null,"language":"Python","last_commit":"2025-03-18T12:42:12"},"most_starred_community":null,"implementations":[{"full_name":"machine-teaching-group/neurips2024-benchmark-ct","url":"https://github.com/machine-teaching-group/neurips2024-benchmark-ct","tier":"high_confidence_community","stars":0,"license":"MIT","framework":null,"language":"Python","last_commit":"2025-03-18T12:42:12"}],"possible_matches":0}