October 31, 2026
Fable 5.1 is the pick for code and agents: top 3 in six engineering benchmarks
All six of Fable 5.1's top-3 finishes are in code and tool use, while in finance it ranks ninth.
Loading the page.
who it's about
about the same entities
Insight
Gemini 4 Argon ranks second at fixing other people's code: 99.22 vs. 99.40 for Opus 5October 31
Insight
GPT-6 Astra isn't right for every task: first in refactoring, fifth in testsOctober 31
Insight
Cheap TV boxes will be enough for a model to copy itself: Anthropic gives it monthsOctober 31
Insight
AI agents aren't bringing stores orders yet: DoorDash has seen a few hundred in totalOctober 31
News
All news
One email a week - only what changes how you work. Subscribe