"Inkling Small from @thinkymachines on ARC-AGI (Verified): - ARC-AGI-2: 40.1%, $0.23/task - ARC-AGI-1: 84%, $0.11/task Inkling Small is the highest-scoring open-weight model evaluated by ARC Prize on both ARC-AGI-1 and ARC-AGI-2, setting a new cost-performance frontier."
Full results: https:// arcprize.org/results/thinky -inkling-small …
ARC-AGI-3 evaluations are more operationally intensive, so results will roll out over the next few weeks. - Leaderboard: https:// arcprize.org/leaderboard - Reproduce the public results: https:// github.com/arcprize/arc-a gi-benchmarking … - Testing policy: https:// arcprize.org/policy - Full Inkling Small results: https:// arcprize.org/results/thinky -inkling-small … — ARC Prize