DeepSeek-V3.2 (Thinking) vs Kimi K2 0905: Specs & Benchmark Comparison
| Characteristic | DeepSeek-V3.2 (Thinking) | Kimi K2 0905 |
|---|---|---|
| Company | DeepSeek | Moonshot AI |
| Release Date | November 30, 2025 | September 5, 2025 |
| Parameters | 685B | 1.0T |
| Multimodal | No | No |
| Context (input) | 131K | 262K |
| Context (output) | 66K | 262K |
| Input Price / 1M | $0.28 | $0.60 |
| Output Price / 1M | $0.42 | $2.50 |
| Average Score | 0.9 | 0.8 |
| Benchmarks | ||
| GPQA | 0.8 | 0.8 |
| MMLU-Pro | 0.8 | 0.8 |
Visual Benchmark Comparison
DeepSeek-V3.2 (Thinking)
Kimi K2 0905
GPQA0.8 vs 0.8
0.8
0.8
MMLU-Pro0.8 vs 0.8
0.8
0.8
Verdict
DeepSeek-V3.2 (Thinking) leads in 2 out of 4 comparison categories.
Overall Performance
Both models show comparable average scores: DeepSeek-V3.2 (Thinking) — 0.9, Kimi K2 0905 — 0.8.
API Cost
DeepSeek-V3.2 (Thinking) is 4.4x cheaper: input $0.28/1M vs $0.60/1M tokens.
Context Window
Kimi K2 0905 supports a larger context: 262K vs 131K tokens.
Recency
DeepSeek-V3.2 (Thinking) is newer: released 11/30/2025 vs 9/5/2025.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — DeepSeek-V3.2 (Thinking) or Kimi K2 0905?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — DeepSeek-V3.2 (Thinking) or Kimi K2 0905?
DeepSeek-V3.2 (Thinking) is cheaper for input: $0.28 per 1M tokens vs $0.60.
Which has a larger context window — DeepSeek-V3.2 (Thinking) or Kimi K2 0905?
Kimi K2 0905 supports a larger context: 262,144 tokens vs 131,072.
The DeepSeek-V3.2 (Thinking) and Kimi K2 0905 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 Kimi K2 0905 page. See also the complete list of AI model comparisons.