Grok 4 is a closed-weights model from xAI, released July 9, 2025. It has an ECI score of 147 and ranks 85th of 240 tracked models. At the time of its release, it ranked 3rd of 125 tracked models.
| Domain | Benchmark | ||||
|---|---|---|---|---|---|
ECI scoreBest score 173 | 147 | 140 | 147 | 145 | |
| Ranking | #85 | #126 | #81 | #96 | |
| Agent | GDPvalBest score 50% | ||||
| Conceptual reasoning | SimpleBenchBest score 95% | ||||
ARC-AGI-2Best score 95% | |||||
ARC-AGI-1Best score 99% | |||||
| Mathematics | OTIS Mock AIME 2024-2025Best score 100% | ||||
| Science | GPQA DiamondBest score 97% | ||||
| 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% |