Open source harness behind the ARC-AGI-3 jump
Claude Opus 5 scores 30% on ARC-AGI-3 on its own, so nearly all of a perfect run comes from the agent scaffolding wrapped around it. A code walkthrough goes through the open source harness line by line to show how that scaffolding works.
The write-up credits a harness built with Strands and puts the final score at 99.95%. NVIDIA's developer blog and The New Stack, though, attribute the 100% result with Claude Opus 5 to NVIDIA's own AVO coding agent, which cleared every level of the benchmark.
Up next
HTTPX2 becomes the default in OpenAI's Python SDK
Certificate verification in the OpenAI Python SDK now leans on the operating-system trust store: HTTPX2 dropped certifi, and minimal container images without system CA certificates can fail outright.
Related stories
Comments
No comments yet. Be the first.
Join the conversation
Sign in with Google to leave a comment. Your name and avatar come from your Google profile, and the comment appears after moderation.