Center for AI Safety
A nonprofit organization focused on artificial intelligence safety research. It co-created evaluation benchmarks such as the Remote Labor Index.
Timeline (last 90 days)
Fable 5.2 reaches a 41% automation rate on the Remote Labor Index (Remark benchmark), whereas a year earlier Opus 4.5 was only about 3.8%, and GPT-6 Astra reached about 21% in September.
The Remote Labor Index was jointly proposed by Scale AI and the Center for AI Safety, and measures the proportion of real remote work tasks that an AI model can complete end-to-end automatically.
All Facts (2)
Fable 5.2 reaches a 41% automation rate on the Remote Labor Index (Remark benchmark), whereas a year earlier Opus 4.5 was only about 3.8%, and GPT-6 Astra reached about 21% in September.
50%UnverifiedThe Remote Labor Index was jointly proposed by Scale AI and the Center for AI Safety, and measures the proportion of real remote work tasks that an AI model can complete end-to-end automatically.
50%