Compare models
Pick up to three models.
 DeepSeek V4 Pro |  Kimi K3 |  Claude Sonnet 5 | |
|---|---|---|---|
| AA Intelligence Index | 44 | 57 | 53 |
| Context window | 1M tokens | 1M tokens | 200K tokens |
| Input $/MTok | $0.435 / MTok | $3 / MTok | $3 / MTok |
| Output $/MTok | $0.87 / MTok | $15 / MTok | $15 / MTok |
| Modalities | text, code | text, image, code | text, image, code |
| API | Yes | Yes | Yes |
| Open source | Yes | Yes | No |
Intelligence Index scores are sourced from Artificial Analysis, an independent evaluator — not Timace's own judgment.