Compare models
Pick up to three models.
 Mistral Large 3 |  GPT-5.1 |  Llama 4 Maverick | |
|---|---|---|---|
| AA Intelligence Index | 16 | 39 | 14 |
| Context window | 128K tokens | 400K tokens | 1M tokens |
| Input $/MTok | $2 / MTok | $1.25 / MTok | — |
| Output $/MTok | $6 / MTok | $10 / MTok | — |
| Modalities | text, image, code | text, image, audio, code | text, image, code |
| API | Yes | Yes | Yes |
| Open source | Yes | No | Yes |
Intelligence Index scores are sourced from Artificial Analysis, an independent evaluator — not Timace's own judgment.