DeepSeek-V3.2 (Thinking) vs Mercury 2: Specs & Benchmark Comparison
| Characteristic | DeepSeek-V3.2 (Thinking) | Mercury 2 |
|---|---|---|
| Company | DeepSeek | Inception |
| Release Date | November 30, 2025 | February 1, 2026 |
| Parameters | 685B | — |
| Multimodal | No | No |
| Context (input) | 131K | — |
| Context (output) | 66K | — |
| Input Price / 1M | $0.28 | — |
| Output Price / 1M | $0.42 | — |
| Average Score | 0.9 | 0.7 |
| Benchmarks | ||
| LiveCodeBench | 0.8 | 0.7 |
| GPQA | 0.8 | 0.7 |
| AIME 2025 | 0.9 | 0.9 |
Visual Benchmark Comparison
DeepSeek-V3.2 (Thinking)
Mercury 2
LiveCodeBench0.8 vs 0.7
0.8
0.7
GPQA0.8 vs 0.7
0.8
0.7
AIME 20250.9 vs 0.9
0.9
0.9
Verdict
Mercury 2 leads in 1 out of 2 comparison categories.
Overall Performance
Both models show comparable average scores: DeepSeek-V3.2 (Thinking) — 0.9, Mercury 2 — 0.7.
Recency
Mercury 2 is newer: released 2/1/2026 vs 11/30/2025.
More About These Models
Related Comparisons
The DeepSeek-V3.2 (Thinking) and Mercury 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 Mercury 2 page. See also the complete list of AI model comparisons.