BenchmarksReasoning
ARC-AGI-3
The interactive ARC-AGI-3 generalization benchmark: agents must learn novel game environments from scratch (semi-private set).
ReasoningaccuracyHigher is better
Dataset/task execution is documented, but frontier submissions are competition-style.
1Expected output
Use the official source links for current output format, submission steps, and benchmark-specific result files.
2Submit results
Keep source URL, source model name, benchmark version, harness, and run context attached to any reported score.
Gotchas
Competition submissions and private/evaluation splits make provenance important.
Do not mix this benchmark's metric with unrelated benchmark metrics.