Arena.ai: Claude Fable 5.1 Writes More Matter-of-Fact but More Verbose
The Decoder · rss · 2026-09-10
Arena.ai analyzed tens of thousands of benchmark responses to track how Claude's writing changed from Fable 5 to Fable 5.1. Their finding: Fable 5.1's language is less 'load-bearing' than its predecessor's — more matter-of-fact in tone, but also more verbose.
More from Models
- OpenAI Claims Navier-Stokes Solved, Substantial Progress on Another Millennium Problem — Dr_Singularity · 2026-09-11
- DeepSeek V4.1 Flash pricing called 'absurdly' cheap — 'intelligence too cheap to meter' — ericwdolan · 2026-09-11
- Analyst: NAND's DRAM moment — DeepSeek V4.1 Flash keeps 26% of params on SSD — casper_hansen_ · 2026-09-11
- Cohere says North Small Translate is proficient across 50+ languages — cohere · 2026-09-11
- Cohere launches open translation model North Small Translate, scoring 83.6 on WMT — cohere · 2026-09-11
- DeepSeek V4.1 Flash reportedly adopts YOCO architecture for order-of-magnitude KV savings — donglixp · 2026-09-11