Claude Fable 5.1 tops benchmarks but costs 20% more per task due to higher token usage
ArtificialAnlys · x · 2026-09-02
Artificial Analysis reports that Claude Fable 5.1 (max) scores 66 on the Intelligence Index, surpassing Claude Opus 5 and GPT-5.6 Sol, with new highs on Terminal-Bench v2.1 and SciCode. Despite a 75% cut in cache read pricing, the cost per task is 20% higher than Fable 5 due to increased output tokens. It leads in agentic tasks like GDPval-AA v2 but trails Opus 5 in presentation quality.
Related event: Fable 5.1 Tops Benchmarks, Cost Debate Erupts(14 posts)→
More from Models
- Experts Question OpenAI Astra Eval Over Contamination and Metagaming Risks — ShakeelHashim · 2026-09-02
- Astra hits 100% success on ExploitBench refresh, reaching 'cyber-critical' threshold — infoxiao · 2026-09-02
- Anthropic Uses Activation Probes to Detect Cybersecurity Threats in Claude — nrehiew_ · 2026-09-02
- RWKV-7 G1j released: pure RNN architecture gets much better at agents and coding — jeremyphoward · 2026-09-02
- Fable 5.1 one-shots a working guitar VST plugin in 30 minutes — CtrlAltDwayne · 2026-09-02
- Fable 5.1 spontaneously solves 373-year-old cipher in 44 minutes — rickasaurus · 2026-09-02