The tweaks to Sonnet 4.6 have taken it past the pricier Opus 4.6 in two of 13 benchmark categories: agentic financial analysis (Finance Agent v1.1, 63.3 percent vs. 60.1 percent) and office tasks (GDPVal-AA Elo, 1633 vs. 1606). Opus 4.6 wins in six of the 13 categories, in tests that show rival Gemini 3 Pro and GPT-5.2 each leading in 2 of 13 categories. But benchmark tests should not be taken too seriously.
Robby Stein from Google wrote on X, "We're seeing big improvements for complex STEM questions." He said he was "Very excited about this week's AI Mode model update." It is great for back to school, he added. The changes are that the responses should be "tighter, easier to scan and get to the point up front before elaborating," he explained.
