We evaluate DeepCode on the PaperBench benchmark (released by OpenAI), a rigorous testbed requiring AI agents to independently reproduce 20 ICML 2024 papers from scratch. The benchmark comprises 8,316 ...
Balancer reported that white hats had managed to recover some of the funds stolen in a $116 million exploit, and Gnosis added ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback