OpenAI's zero-intervention success on 4-8h research tasks rose ~25% in 6 months — but task mix confounds it

daveholtz · x · 2026-11-19

Ben Todd relays that OpenAI's success rate on real 4-8h AI research tasks completed without human intervention has risen 25% in 6 months; at that pace it saturates in 14 months, with a doubling time of 4 months versus the 2-3 months Anthropic found.

daveholtz, involved in the report, flags a key caveat: researchers endogenously choose which tasks to point AI at, so movement in these rates reflects both (1) improving model capability and (2) shifts in the chosen task bundle — it is not performance on a static, shared benchmark, which may explain differences between labs' numbers.

Original post →

More from AGI Musings

AGI Musings channel →