How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Fable 5.2 vs Fable 5.1: Coding Benchmark Results

calendar_today November 12, 2026 person Snorkel Team domain snorkel-ai

Fable 5.2 pass@1 score lands at 71% compared to Fable 5.1 score of 53% on a set of 26 frontier coding tasks. The mid-run terminal failures that appeared in the analysis of Fable 5.1 nearly disappear when examining Fable 5.2. The post Fable 5.2 vs Fable 5.1: Coding Benchmark Results appeared first on Snorkel AI .

open_in_new Read original post