xAI launched Grok 4.7 on September 21, 2026. The model took first, second and third place on the VulcanBench Frontier v4 leaderboard with scores of 93.15 at extra-high effort, 92.71 at high effort and 92.30 at medium effort. The closest rival, Claude Fable 5.1, scored 91.84, which is 1.31 points lower than Grok 4.7’s extra-high setting. At the extra-high effort level, Grok 4.7 passed all 23 behavioral-reconstruction tasks on the benchmark. Pricing remains unchanged from Grok 4.6 at 2 dollars per million input tokens and 6 dollars per million output tokens.
Source: Read the original article
Disclaimer: this content is for information purposes only and is not financial advice. Cryptocurrencies are highly volatile: you may lose all of your capital. Always do your own research. Legal notice
