Re:Gemini 3 for developers: New reasoning, agentic capabilities
by mudkipdev on Tuesday November 18, 2025 @11:55AM
(#45968840)
I make my own automated benchmarks
[ Parent
| on HN ]
Re:Gemini 3 for developers: New reasoning, agentic capabilities
by ummonk on Tuesday November 18, 2025 @01:43PM
(#45970257)
Is there a tool / website that makes this process easy?
Re:Gemini 3 for developers: New reasoning, agentic capabilities
by mudkipdev on Tuesday November 18, 2025 @01:54PM
(#45970390)
I coded it bun and openrouter(dot)ai. I have an array of benchmarks, each benchmark has a grader (for example, checking if it equals a certain string or grade the answer automatically using another LLM). Then I save all results to a file and render the percentage correct to a graph