Gemini 3 Deep Think: benchmark scores, price and ranking
Gemini 3 Deep Think from Google DeepMind ranks #60 of 743 LLMs on the LLMs Tiger aggregate benchmark score (52.6), based on 1 benchmark results captured up to 2026-10-13.
- Organisation
- Google DeepMind
- Type
- Frontier model
- Open weights
- No
- Released
- 2026-02-12 (source: epoch)
- Aggregate rank
- #60 of 743 (score 52.6)
Across the 1 benchmark where at least ten models are scored, Gemini 3 Deep Think is in the top 10% on 0 and in the top half on 1.
Gemini 3 Deep Think benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| CritPt | 25.7% | #14 of 115 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Gemini 3 Deep Think
Gemini 3 Deep Think is a frontier model from Google DeepMind. It was released on 2026-02-12, according to Epoch AI. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where Gemini 3 Deep Think stands
On our aggregate score, Gemini 3 Deep Think is #60 of 743 ranked models, in the top quarter. Its score is 52.6; the scale is centred on 50, so it sits 2.6 points above the typical model. That beats 92% of the ranked field. Among the 41 ranked Google DeepMind models it is #4. The next one up is Gemini 3 Pro Preview at 53.7. The next one down is AI co-mathematician at 52.3.
Gemini 3 Deep Think, benchmark by benchmark
CritPt puts Gemini 3 Deep Think at 25.7%, #14 of 115. That beats 88% of the models tested, but 6.6 points short of GPT-5.6 Sol (max) (32.3%). The results either side are mimo-v2.6-pro (26.6%) and Muse Spark 1.3 (max) (24.9%). It covers unpublished research-level physics problems. The board median is 2.9%, so Gemini 3 Deep Think is 22.9 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Release history
The Google DeepMind model released before it was Gemini 3 Flash on 2025-12-17, which scores 51.5. The next one was Gemma 4 26B A4B on 2026-04-02, at 47.5.
Reading these numbers
The 1 score on this page comes from 1 source: Epoch AI Benchmarking Hub (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #57 Codex + GPT-6 Astra (52.6)
- #58 Codex + GPT-6.1 Sol (52.6)
- #59 Gemini 2.5 Pro Preview 03-25 (52.6)
- #61 Claude Code + Fable 5.1 (52.6)
- #62 claude-opus-4-20250514 (52.5)
- #63 Claude Opus 4.6 (max) (52.5)
More from Google DeepMind
- Gemini 3.8 Flash (high) (#26, 54.0)
- Gemini 3.7 Flash (high) (#27, 53.9)
- Gemini 3 Pro Preview (#31, 53.7)
- AI co-mathematician (#69, 52.3)
- Gemini 3 Flash (#120, 51.5)
- Gemini 2.5 Pro Exp (Mar 2025) (#140, 51.2)
Compare it on the live leaderboard → · How the aggregate score works