Grok 4 is a closed-weights model from xAI, released July 9, 2025. It has an ECI score of 146 and ranks 71st of 253 tracked models. At the time of its release, it ranked 3rd of 148 tracked models.
| Domain | Benchmark | ||||
|---|---|---|---|---|---|
ECI scoreBest score 167 | 146 | 140 | 147 | 145 | |
| Ranking | #71 | #110 | #62 | #81 | |
| Agent | GDPvalBest score 50% | ||||
| Conceptual reasoning | ARC-AGI-2Best score 95% | ||||
ARC-AGI-1Best score 99% | |||||
| Games | Chess PuzzlesBest score 72% | ||||
| Mathematics | OTIS Mock AIME 2024-2025Best score 100% | ||||
| Science | GPQA DiamondBest score 96% | ||||
| Software engineering | METR Time HorizonsBest score 17 hr 25 min | 1 hr 50 min | — | — | 38 min 44 sec |
Terminal-Bench 2.0Best score 85% | |||||
Aider PolyglotBest score 88% |