Research & KnowledgeEvent: September 8, 2026
Google Cloud evaluated agents across 113 complex, multi-repo software engineering problems using DeepSWE 1.1, where Gemini 3.8 Flash scored 73.7% and Claude Opus 5 scored 74.0%
Published
Signal category
Research & Knowledge
Quote
“On DeepSWE 1.1, which evaluates agents across 113 complex, multi-repo software engineering problems, Gemini 3.8 Flash scored 73.7%. That puts it in a dead heat with Claude Opus 5 (74.0%).”
— Brandon Seppa|Google team
Company
- Industry
- Software Development
- Location
- Mountain View, US
- Company size
- 296,721 employees
A problem isn't truly solved until it's solved for all. Googlers build products that help create opportunities for everyone, whether down the street or across the globe. Bring your insight, imagination and a healthy disregard for the impossible. Bring everything that makes you unique. Together, we can build for everyone. Check out our career opportunities at goo.gle/3DLEokh