DeepSeek-V3.2 Thinking
by DeepSeek
+
+
+
+
About
DeepSeek-V3.2-Exp (DeepSeek-V3.2 Thinking), released by DeepSeek in September 2025, is the experimental preview release of the DeepSeek-V3.2 model featuring 685 billion total parameters and integrated thinking capabilities. It introduced the architecture and training approaches that became the foundation of the final V3.2 release, including thinking in tool-use and hybrid reasoning modes.
+
+
+
+
Pricing Range
Input (per 1M)$0.55 -$0.55
Output (per 1M)$2.19 -$2.19
Providers1
+
+
+
+
Timeline
ReleasedSep 29, 2025
+
+
+
+
License & Family
License
MIT
Performance Overview
Performance metrics and category breakdown
Overall Performance
1 benchmarks
Average Score
73.1%
Best Score
73.1%
High Performers (80%+)
0Performance Metrics
Max Context Window
136.0KTop Categories
Coding
73.1%
+
+
+
+
All Benchmark Results for DeepSeek-V3.2 Thinking
Complete list of benchmark scores with detailed information
| SWE Bench Verified | Coding | 73.10 | 73.1% | Unverified |