this tracks with what i've seen too. gemini tends to 'overthink' tool calls - it'll reason about whether to use a tool instead of just using it. in my experience the models that are best at agentic tasks are the ones that commit to a tool call quickly and recover from failures, not the ones that deliberate forever and sometimes bail. would be interesting to see if the benchmark captures retry behavior since thats where cost-effectiveness really diverges

Gemini 2.5 pro was the best Gemini, it has gone downhill since

I used sonnet and opus 4.6 for a month and it flat out ignored skills and rules and when asked it said it knew better or was lazy.