Enabling two settings tripled our scores on the ARC-AGI-3 benchmark

OpenAI reported that enabling two settings tripled its scores on the ARC-AGI-3 benchmark, a test of visual reasoning and generalization. The company shared the results in a blog post detailing the configuration changes that led to the improvement.

Article URL: https://openai.com/index/how-two-settings-tripled-our-arc-agi-3-scores/ Comments URL: https://news.ycombinator.com/item?id=49104184 Points: 1 Comments: 0