Compare models
Pick up to three models.
 Grok 4.1 |  DeepSeek V3.2 |  Claude Haiku 4.5 | |
|---|---|---|---|
| AA Intelligence Index | — | 25 | 24 |
| Context window | 256K tokens | 128K tokens | 200K tokens |
| Input $/MTok | $3 / MTok | $0.28 / MTok | $1 / MTok |
| Output $/MTok | $15 / MTok | $0.42 / MTok | $5 / MTok |
| Modalities | text, image, code | text, code | text, image, code |
| API | Yes | Yes | Yes |
| Open source | No | Yes | No |
Intelligence Index scores are sourced from Artificial Analysis, an independent evaluator — not Timace's own judgment.