OpenAI News·· 20 d ago
Cognition helps Devin test its own work with GPT‑6 Astra
Cognition helps Devin test its own work with GPT‑6 Astra
AI summary
Cognition uses GPT-6 Astra to improve Devin's ability to test software and demonstrate that it works, aiming to reduce engineers' code review burden and speed up delivery.
Selection record
Threshold 60Official, first-handFirst 34Second 42
Not admittedSum of both 76 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：OpenAI模型用于Devin软件测试
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: OpenAI News · openai.com