Google Carbon Report - AA-Omniscience 6000 questions - Index: leaderboard
Google DeepMind Carbon safety report, Figure 5.12. 6000 questions across 42 topics/six domains; correct minus incorrect-guess reward. This is Google-run original 6000-question benchmark, NOT current AA v1.1 3000-question primary source. Metric: Omniscience Index. Higher is better. Source: https://storage.googleapis.com/deepmind-media/gemini/gemini_4_carbon_safety_report.pdf#page=75
Metric: Omniscience Index. Source: storage.googleapis.com. Saturation forecast: Around January 2028. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Carbon | 53.5 | #2 |
| 2 | Gemini 4 Argon | 46.1 | #11 |
| 3 | Gemini 3.8 Flash | 23.3 | #36 |
No result here: #1 Claude Fable 5.2, #5 Claude Opus 5.5, #6 GPT-6 Astra.
Interactive version: theaggregate.ai/benchmark?slug=google-carbon-report-aa-omniscience-6000-questions-index · How It Works · Data refreshed daily, snapshot 2026-11-12.