Arena.ai Compares Fable 5.1 to Other AI Models
Company shares head-to-head evaluation of new model across coding and research tasks.
TLDR
Arena.ai posted asking whether Anthropic's newly released Fable 5.1 is actually better. The post references a head-to-head evaluation by @petergostev of Fable 5.1 against Fable 5, Opus 5, GPT-5.6, Kimi K3, GLM 5.3, Qwen-3.8, Grok-4.6, and DeepSeek. Tasks included coding, 3D, SVG, research, and data-viz. Generation costs ranged from cents to over $65. A linked YouTube video titled Claude Fable 5.1 | First impressions covers the results and is hosted at arena.ai/agent.
Combined views
45.1K
1 Source, first seen ago