Compare models
Pick up to three models.
 DeepSeek V4 Pro |  Qwen3 235B |  Claude Haiku 4.5 | |
|---|---|---|---|
| AA Intelligence Index | 44 | 20 | 24 |
| Context window | 1M tokens | 256K tokens | 200K tokens |
| Input $/MTok | $0.435 / MTok | — | $1 / MTok |
| Output $/MTok | $0.87 / MTok | — | $5 / MTok |
| Modalities | text, code | text, 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.