DeepSeek-V3.2 (Thinking) vs MiniMax M2.1: Specs & Benchmark Comparison
| Characteristic | DeepSeek-V3.2 (Thinking) | MiniMax M2.1 |
|---|---|---|
| Company | DeepSeek | MiniMax |
| Release Date | November 30, 2025 | December 22, 2025 |
| Parameters | 685B | — |
| Multimodal | No | No |
| Context (input) | 131K | 1.0M |
| Context (output) | 66K | 100K |
| Input Price / 1M | $0.28 | $0.30 |
| Output Price / 1M | $0.42 | $1.20 |
| Average Score | 0.9 | 0.9 |
| Benchmarks | ||
| MMLU-Pro | 0.8 | 0.9 |
| GPQA | 0.8 | 0.8 |
Visual Benchmark Comparison
DeepSeek-V3.2 (Thinking)
MiniMax M2.1
MMLU-Pro0.8 vs 0.9
0.8
0.9
GPQA0.8 vs 0.8
0.8
0.8
Verdict
MiniMax M2.1 leads in 2 out of 4 comparison categories.
Overall Performance
Both models show comparable average scores: DeepSeek-V3.2 (Thinking) — 0.9, MiniMax M2.1 — 0.9.
API Cost
DeepSeek-V3.2 (Thinking) is 2.1x cheaper: input $0.28/1M vs $0.30/1M tokens.
Context Window
MiniMax M2.1 supports a larger context: 1M vs 131K tokens.
Recency
MiniMax M2.1 is newer: released 12/22/2025 vs 11/30/2025.
More About These Models
Related Comparisons
The DeepSeek-V3.2 (Thinking) and MiniMax M2.1 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 MiniMax M2.1 page. See also the complete list of AI model comparisons.