← People

Ryan Burnell

Source-listed: Research Scientist · Google DeepMind

  • Multimodal AI
  • Language models
  • Evaluation

Selected work

5
  1. Measuring Progress Toward AGI: A Cognitive FrameworkFirst author · 2026
  2. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextAuthor · 2024
  3. Rethink reporting of evaluation results in AIFirst author · 2023
  4. Revealing the structure of language model capabilitiesFirst author · 2023
  5. Not a Number: Identifying Instance Features for Capability-Oriented EvaluationContributor · 2022

Source-linked involvement

1
  1. Gemma 4 Technical ReportAuthor · 2026