DeepSeek-V3.2 (Thinking) vs GPT-5.2: Specs & Benchmark Comparison
| Characteristic | DeepSeek-V3.2 (Thinking) | GPT-5.2 |
|---|---|---|
| Company | DeepSeek | OpenAI |
| Release Date | November 30, 2025 | December 10, 2025 |
| Parameters | 685B | — |
| Multimodal | No | Yes |
| Context (input) | 131K | 256K |
| Context (output) | 66K | 128K |
| Input Price / 1M | $0.28 | $1.50 |
| Output Price / 1M | $0.42 | $6.00 |
| Average Score | 0.9 | 1.0 |
| Benchmarks | ||
| GPQA | 0.8 | 0.9 |
| HMMT 2025 | 0.9 | 1.0 |
| AIME 2025 | 0.9 | 1.0 |
Visual Benchmark Comparison
DeepSeek-V3.2 (Thinking)
GPT-5.2
GPQA0.8 vs 0.9
0.8
0.9
HMMT 20250.9 vs 1.0
0.9
1.0
AIME 20250.9 vs 1.0
0.9
1.0
Verdict
Both models show equal results — the choice depends on your specific use case.
Overall Performance
Both models show comparable average scores: DeepSeek-V3.2 (Thinking) — 0.9, GPT-5.2 — 1.0.
API Cost
DeepSeek-V3.2 (Thinking) is 10.7x cheaper: input $0.28/1M vs $1.50/1M tokens.
Context Window
GPT-5.2 supports a larger context: 256K vs 131K tokens.
Recency
Both models were released around the same time: 11/30/2025 and 12/10/2025.
More About These Models
Related Comparisons
The DeepSeek-V3.2 (Thinking) and GPT-5.2 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the DeepSeek-V3.2 (Thinking) or GPT-5.2 page. See also the complete list of AI model comparisons.