90.0% on ARC-AGI-2 at $4.49 per task
ARC Prize published verified ARC-AGI scores for Claude Fable 5.1, and every result carries a price tag per task. At max reasoning effort the model hits 97.5% on ARC-AGI-1 Semi-Private for $1.40 per task and 90.0% on ARC-AGI-2 Semi-Private for $4.49 per task.
Five reasoning variants were tested. The XHigh setting matches Max on ARC-AGI-2 at 90.0% and trails it by one point on ARC-AGI-1, at 96.5%. The Low setting drops to 78.3% on ARC-AGI-2.
Up next
Cache reads drop 75% with Fable 5.1
Anthropic says Fable 5.1’s cyber safeguards are “less likely to flag benign content” and intervene about 60% less per session, though penetration testing and exploit generation still get routed to Opus.
Related stories
- Claude Sonnet 5.5 keeps Sonnet 5’s price, cuts cost per task
- Meituan’s LongCat-2.5 runs 49B of its 1.6T parameters
- Mistral Large 4 weights are out, API now from $0.70 per 1M
- Opus 5.5 edges GPT-6 Astra, 58 to 57, on Artificial Analysis
- Kimi K3.1 Pro takes #8 on WebDev Arena, 9 spots above K3
- DeepSeek’s minor Flash update beats Opus 5 on DeepSWE
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.