Up to four models
Grok 4.1 Fast vs DeepSeek-V3.2-Speciale
On the index (GPT-4 = 100), Grok 4.1 Fast scores 144 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
Grok 4.1 Fast and DeepSeek-V3.2-Speciale are too close to call (1 point apart, within the uncertainty).
Test by testthird-party results
Grok 4.1 Fast
DeepSeek-V3.2-Speciale
Every result as a table
| Test | Grok 4.1 Fast | DeepSeek-V3.2-Speciale |
|---|---|---|
| Reasoning & knowledge | ||
| SimpleBench | 56.0% | 52.6% |
Tests at least two of these models have taken. Bold rows are the core tests.