DeepSeek-V3.1 vs Kimi K2-Thinking-0905: Specs & Benchmark Comparison
| Characteristic | DeepSeek-V3.1 | Kimi K2-Thinking-0905 |
|---|---|---|
| Company | DeepSeek | Moonshot AI |
| Release Date | January 9, 2025 | September 4, 2025 |
| Parameters | 671B | 1.0T |
| Multimodal | No | No |
| Context (input) | 164K | 262K |
| Context (output) | 164K | 66K |
| Input Price / 1M | $0.27 | $0.60 |
| Output Price / 1M | $1.00 | $2.40 |
| Average Score | 0.8 | 0.9 |
| Benchmarks | ||
| GPQA | 0.8 | 0.8 |
| MMLU-Redux | 0.9 | 0.9 |
| MMLU-Pro | 0.8 | 0.8 |
Visual Benchmark Comparison
DeepSeek-V3.1
Kimi K2-Thinking-0905
GPQA0.8 vs 0.8
0.8
0.8
MMLU-Redux0.9 vs 0.9
0.9
0.9
MMLU-Pro0.8 vs 0.8
0.8
0.8
Verdict
Kimi K2-Thinking-0905 leads in 2 out of 4 comparison categories.
Overall Performance
Both models show comparable average scores: DeepSeek-V3.1 — 0.8, Kimi K2-Thinking-0905 — 0.9.
API Cost
DeepSeek-V3.1 is 2.4x cheaper: input $0.27/1M vs $0.60/1M tokens.
Context Window
Kimi K2-Thinking-0905 supports a larger context: 262K vs 164K tokens.
Recency
Kimi K2-Thinking-0905 is newer: released 9/4/2025 vs 1/9/2025.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — DeepSeek-V3.1 or Kimi K2-Thinking-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-V3.1 or Kimi K2-Thinking-0905?
DeepSeek-V3.1 is cheaper for input: $0.27 per 1M tokens vs $0.60.
Which has a larger context window — DeepSeek-V3.1 or Kimi K2-Thinking-0905?
Kimi K2-Thinking-0905 supports a larger context: 262,144 tokens vs 163,840.
The DeepSeek-V3.1 and Kimi K2-Thinking-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-V3.1 or Kimi K2-Thinking-0905 page. See also the complete list of AI model comparisons.