Google Gemini 3 Deep Think - CMT-Benchmark: leaderboard
The "CMT-Benchmark" subtask of Google Gemini 3 Deep Think. A benchmark result reported for Google Gemini 3 Deep Think, as self-reported by the model developer.
Metric: Pass@8 (%). Source: storage.googleapis.com. Saturation forecast: Around March 2028. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Deep Think | 50.5 | #27 |
| 2 | GPT-5.2 (xHigh) | 41 | #110 (GPT-5.2) |
| 3 | Gemini 3 Pro (Preview) | 39.5 | #66 |
| 4 | Claude Opus 4.6 (Thinking) | 17.1 | #63 (Claude Opus 4.6) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=google-gemini-3-deep-think-cmt-benchmark · How It Works · Data refreshed daily, snapshot 2026-10-20.