Measuring Autonomous AI Research
We ran 153 autonomous runs across 18 frontier models on the nanoGPT optimizer speedrun.
Elie Bakouch
A new class of intelligence for coding and professional work.
We ran 153 autonomous runs across 18 frontier models on the nanoGPT optimizer speedrun.
A new class of intelligence for coding and professional work.
OpenAI
Our most capable model, built for the hardest end-to-end work.
OpenAI
GPT-5.6 model optimized for cost-sensitive workloads.
OpenAI
GPT-5.6 model that balances intelligence and cost.
An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.