Saturday, August 29, 2026
DeepMind pilots double-blind evaluations of Gemini
Google DeepMind said on August 27 it is running what it calls the first double-blind evaluation of a proprietary frontier-class model, testing a Gemini Flash Lite system against confidential benchmarks inside a cryptographically sealed Google Cloud Confidential Space environment. Partners include the Singapore AI Safety Institute, OpenMined, AVERI, and MLCommons; the setup is designed so evaluators cannot see Gemini weights and Google cannot see the test prompts, addressing benchmark contamination as models get more capable.
/ Sources
/ About this story
Compiled by Venture Atlas from the sources above, using automated AI-assisted research. This is a summary of reporting published elsewhere, not original reporting - follow the source links for the full account. See our editorial standards.
Something wrong here? Email flightatlas.contact@gmail.com and we will fix it.
/ Related
- Google moves DeepMind's AI safety team into Global AffairsFriday, August 28, 2026
- Google DeepMind's Gemma open models pass 1 billion downloadsSunday, August 23, 2026
- Hassabis moves to Chairman as Google's Jeff Dean departsMonday, August 17, 2026
- Google DeepMind launches Gemini 3.7 Flash at half the priceSunday, August 16, 2026