DeepSWE and FrontierCode are more realistic if you read up on what they actually measure. But the most realistic is to try it yourself. Benchmarks can only vaguely represent typical usage, and how you judge the result. Giving the same real task you have to a few models will make you understand them better than chasing benchmarks.

When? It literally says on the page for Gemini 3.6 Flash "Artificial Analysis Coding Index represents the weighted average of coding benchmarks in the Artificial Analysis Intelligence Index (Terminal-Bench v2.1, SciCode)"

My bad it was the coding agent index