OpenAI has revealed that its flagship GPT-5.6 Sol model, capable of cracking open problems in mathematics, was being held back on a benchmark of unfamiliar 2D puzzle games not by the model itself but by the way it was being run. After investigating why Sol struggled with ARC-AGI-3, the company said enabling two API settings raised its score on the public task set by roughly 188 percent while cutting output token usage to a sixth of what it had been.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.