ainewsblitz.com

Breaking

OpenAI Says Two API Settings Tripled GPT-5.6 Sol's Score on ARC-AGI-3 Puzzle Benchmark

OpenAI Says Two API Settings Tripled GPT-5.6 Sol's Score on ARC-AGI-3 Puzzle Benchmark
  • Foundation Models
  • AI Agents
  • Research & Papers

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.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year