Schema Harness Achieves ~99% on Arc‑AGI‑3 Public
What happened
Researchers have introduced Schema Harness, a new approach that scored nearly 99% on the public ARC-AGI-3 benchmark. This benchmark is designed to test an AI's ability to learn and adapt to entirely new visual puzzle rules on the fly, moving beyond mere memorization. This high score demonstrates a major leap in artificial general intelligence reasoning capabilities.
Why it matters
This breakthrough suggests we are getting closer to AI systems that can genuinely reason and solve novel problems like humans do, rather than just pattern-matching existing data. It could soon lead to more adaptable software agents capable of autonomous problem-solving in unpredictable real-world environments.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More AI news
Show HN: New Cartesia Text-to-Speech ModelIndustry news · 13 Nov 2026Chicago schools to Google – we'd rather lose Search than be forced to accept AIIndustry news · 13 Nov 2026Introducing ChatGPT WalletOpenAI · 13 Nov 2026Shield helps technicians hand off legacy portal work with OpenAIOpenAI · 13 Nov 2026How AI Is Helping Care Teams Get Patients the Right Care, SoonerNVIDIA · 13 Nov 2026This page was collected from schema-harness.github.io and summarised automatically by AIPulsee's pipeline. See how it runs.