NVIDIA AVO scores 100% on ARC-AGI-3 interactive reasoning benchmark

Nvidia AVO scores 100% on the ARC-AGI-3 interactive reasoning benchmark

NVIDIA AVO scores 100% on ARC-AGI-3 interactive reasoning benchmark

NVIDIA's general-purpose coding agent AVO scored 100% on the ARC-AGI-3 interactive reasoning benchmark, completing all 183 levels across 25 public environments without instructions, explicit rules, or stated goals. The company says AVO continuously inspects, plans, implements, and evaluates, using memory and tools to sustain progress on long-running tasks.

Our general-purpose coding agent just scored 100% on the ARC-AGI-3 interactive reasoning benchmark.

More from this day

2026-08-21