Google rolled out Gemini 3.1 Pro yesterday, touting a 77.1% score on novel logic puzzles that models can't just memorize—more than double 3 Pro's result—and record marks for expert-level scientific ...
Use the vitals package with ellmer to evaluate and compare the accuracy of LLMs, including writing evals to test local models ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results