Grok-2 (Dec 2024) is a closed-weights model from xAI, released December 12, 2024. It has an ECI score of 130 and ranks 148th of 249 tracked models. At the time of its release, it ranked 6th of 100 tracked models. At $2/Mtok for input tokens and $10/Mtok for output tokens, it is more expensive per token than similarly-capable models.
| Domain | Benchmark | ||||
|---|---|---|---|---|---|
ECI scoreBest score 166 | 130 | 130 | 129 | 132 | |
| Ranking | #148 | #149 | #157 | #143 | |
| Conceptual reasoning | SimpleBenchBest score 81.9% | ||||
| Mathematics | MATH Level 5Best score 98.1% | ||||
OTIS Mock AIME 2024-2025Best score 100.0% | |||||
| Science | GPQA DiamondBest score 95.8% | ||||
| Software engineering | WeirdML (v2)Best score 92.9% | ||||
| Writing & creativity | Lech Mazur WritingBest score 8.6 | 6.4 | 6.3 | 8.2 | — |
| Other | LiveBenchBest score 82.3% |