Grok 4.5 Tops τ³-Banking Benchmark Ahead of GPT-5.5 and Claude Models
On X, Elon Musk reposted a claim from @XFreeze that xAI's Grok 4.5 is ranked No. 1 on Artificial Analysis' τ³-Banking benchmark, ahead of GPT-5.5 xhigh and Claude models. A second high-circulation repost from Andreessen Horowitz partner Martin Casado broadened the message, saying Grok 4.5 looks No. 1 on "at least a few benchmarks." So far, the public evidence in view is the posts themselves, not independent reporting or benchmark documentation.
Combined views
384.1K
2 posts, first seen 10h ago
Grok 4.5 Tops τ³-Banking Benchmark Ahead of GPT-5.5 and Claude Models
On X, Elon Musk reposted a claim from @XFreeze that xAI's Grok 4.5 is ranked No. 1 on Artificial Analysis' τ³-Banking benchmark, ahead of GPT-5.5 xhigh and Claude models. A second high-circulation repost from broadened the message, saying Grok 4.5 looks No. 1 on "at least a few benchmarks." So far, the public evidence in view is the posts themselves, not independent reporting or benchmark documentation.
Combined views
384.1K
2 posts, first seen 10h ago