ainewsblitz.com

Breaking

OpenAI's GPT-5.6 Sol Scores 7.8% on Verified ARC-AGI-3 Leaderboard, Trailing Claude Opus 5 Despite 'SoTA' Claim

OpenAI's GPT-5.6 Sol Scores 7.8% on Verified ARC-AGI-3 Leaderboard, Trailing Claude Opus 5 Despite 'SoTA' Claim
  • Foundation Models
  • AI Agents
  • Research & Papers

OpenAI's GPT-5.6 Sol holds a verified score of 7.8% on the ARC-AGI-3 benchmark, according to ARC Prize's official leaderboard—well short of the state-of-the-art claim made for the model and still behind Anthropic's Claude Opus 5, which leads with 30.2%. The gap stems from a dispute over how the benchmark should be run, and it has turned into a case study in how much an AI system's performance depends on the software scaffolding wrapped around the underlying model.

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