ARC Prize publishes Claude Fable 5.2's evaluation results on the various versions of ARC-AGI
ARC Prize published the results of Anthropic's Claude Fable 5.2 on ARC-AGI: under the ARC-AGI-3 standard testing framework it scored 81.2% at a cost of $21.9K, ARC-AGI-2 scored 93.8% at $0.98 per task, and ARC-AGI-1 scored 98.5% at $0.36 per task. The 93.8% on ARC-AGI-2 is the third-highest model score it has seen, behind only GPT-6 Astra's 95.0% and GPT-6.1 Sol's 94.2%. At the max reasoning level, 28 of the 55 semi-private games hit the 12-hour runtime limit, scoring 65.7%, lower than the 81.2% at the xhigh level.
Why read this
SelectedAI score 74
ARC Prize published Claude Fable 5.2's scores and per-task costs on three versions of ARC-AGI, allowing comparison of its ranking gap with the GPT-6 series.
Topics
Body
@AnthropicAI Join ARC Prize @ NeurIPS 2026 on December 12, 6-9 PM in Atlanta for a rooftop happy hour near the convention center.
Space is limited and registration requires host approval: https://t.co/1cdZppwijd