DeepSeek

DeepSeek-V3.2 Thinking

by DeepSeek

+
+
+
+
About

DeepSeek-V3.2 Thinking is the experimental preview release of DeepSeek-V3.2, made available by DeepSeek in September 2025 to give researchers and developers early access to the model's integrated thinking capabilities before the full December release. It preceded the broader V3.2 availability and gave early adopters a chance to test the model's approach to embedding reasoning into tool-use flows.

+
+
+
+
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%+)
0

Performance Metrics

Max Context Window
136.0K

Top 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