Gemini 3 Deep Think
A specialized frontier reasoning mode for difficult science, mathematics, research, and engineering, available to Ultra users with selected API access.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 72.4
Exceptional broad reasoning and demonstrated scientific work support high capability, while specialized access and limited general action surfaces constrain autonomy and deployment.
News tied to Gemini 3 Deep Think
The model score of 72.4 rates this model's risk profile. The overall Doom Index of 67.9 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores use a bounded temporal offset around their technical profile, but never feed back into the overall index.
Gemini 3 Deep Think advances frontier reasoning for science and engineering
Google DeepMind released an upgraded specialized reasoning mode with 84.6% on ARC-AGI-2, broad frontier evaluations, Ultra access, and selected API access. Early testers reported finding a peer-review flaw and producing a semiconductor fabrication recipe.
- Full item contribution
- +0.17
- Gemini 3 Deep Think equal share
- +0.17
Model score history
-
R4
Doom Score 72.4
Source-backed model availability audit using the model's existing primary or authoritative catalogue evidence. Exact-version evidence chronology replayed under temporal-monthly-pressure-v4.
12 Aug 2026 -
R3
Doom Score 72.4
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R2
Doom Score 72.6
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026 -
R1
Doom Score 72.3
New exact dated model tier absent from durable context.
11 Aug 2026