Grok 3 is a closed-weights model from xAI, released April 9, 2025. It has an ECI score of 137 and ranks 133rd of 240 tracked models. At the time of its release, it ranked 6th of 102 tracked models.
| Domain | Benchmark | ||||
|---|---|---|---|---|---|
ECI scoreBest score 173 | 137 | 130 | 137 | 136 | |
| Ranking | #133 | #158 | #134 | #136 | |
| Conceptual reasoning | SimpleBenchBest score 95% | ||||
ARC-AGI-2Best score 95% | |||||
ARC-AGI-1Best score 99% | |||||
| Long context | Fiction.liveBenchBest score 97% | ||||
| Mathematics | MATH Level 5Best score 98% | ||||
OTIS Mock AIME 2024-2025Best score 100% | |||||
| Science | GPQA DiamondBest score 97% | ||||
| Software engineering | Aider PolyglotBest score 88% | ||||
WeirdML (v2)Best score 94% |