Up to four models
Gemini 3 Pro vs DeepSeek-V3.2-Speciale
On the index (GPT-4 = 100), Gemini 3 Pro scores 160 and DeepSeek-V3.2-Speciale 143. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
143125–162
WeightsOpen
ReleasedDec 2025
Price in / out–
Context–
Core tests taken0 of 9
Gemini 3 Pro leads DeepSeek-V3.2-Speciale by 17 points.
Test by testthird-party results
Every result as a table
| Test | Gemini 3 Pro | DeepSeek-V3.2-Speciale |
|---|---|---|
| Reasoning & knowledge | ||
| SimpleBench | 76.4% | 52.6% |
| Coding | ||
| WeirdML | 69.9% | 46.7% |
Task length · METR
43 sec
Tests at least two of these models have taken. Bold rows are the core tests.