--- format: "aidr-story-markdown/v1" id: "1c817a56250db2af592891d57f03ddb4705dbcd51983ceefc4515d5f627d8c82" canonical_url: "https://aidr.today/1c817a56?lang=en" title: "Nvidia AVO scores 100% on the ARC-AGI-3 interactive reasoning benchmark" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-08-21T13:26:03.000Z" category: "Research" topics: ["nvidia","agent","reasoning","arc-agi-2","coding","anthropic","claude","benchmark"] source_urls: ["https://twitter.com/NVIDIAAI/status/2090786258981466231","https://news.ycombinator.com/item?id=49387755","https://x.com/NVIDIAAI/status/2090786258981466231","https://x.com/NVIDIAAI/status/2090787290306228541","https://x.com/wallstengine/status/2090805759227617586","https://x.com/mark_k/status/2090810812294127699","https://x.com/Hesamation/status/2090826792349102085","https://x.com/ClementDelangue/status/2090797724610318611"] summary: "Our general-purpose coding agent just scored 100% on the ARC-AGI-3 interactive reasoning benchmark. NVIDIA AVO completed all 183 levels across all 25 public environments, figuring out what to do with no instructions, explicit rules, or stated goals." --- # Nvidia AVO scores 100% on the ARC\-AGI\-3 interactive reasoning benchmark > [Open the canonical story]() **Published:** 2026-08-21T13:26:03.000Z **Category:** Research **Topics:** nvidia, agent, reasoning, arc\-agi\-2, coding, anthropic, claude, benchmark ## Summary Our general\-purpose coding agent just scored 100% on the ARC\-AGI\-3 interactive reasoning benchmark\. NVIDIA AVO completed all 183 levels across all 25 public environments, figuring out what to do with no instructions, explicit rules, or stated goals\. ## Sources - [Story source]() - [Discussion]() - [Story source]() - [Story source]() - [Supporting source]() - [Supporting source]() - [Supporting source]() - [Supporting source]()