Compare models
Pick up to three models.
 Kimi K2 |  DeepSeek V3.2 | Kimi K3 | |
|---|---|---|---|
| AA Intelligence Index | 19 | 25 | 57 |
| Context window | 256K tokens | 128K tokens | 1M tokens |
| Input $/MTok | $0.6 / MTok | $0.28 / MTok | $3 / MTok |
| Output $/MTok | $2.5 / MTok | $0.42 / MTok | $15 / MTok |
| Modalities | text, code | text, code | text, image, code |
| API | Yes | Yes | Yes |
| Open source | Yes | Yes | Yes |
Intelligence Index scores are sourced from Artificial Analysis, an independent evaluator — not Timace's own judgment.