OpenCode Go models usage to performance chart

I created this chart to help me quickly pick the best value model at the moment. This chart is updated to current Go plan status (2x GLM-5.3-Flash). The blue bar represents usage limits of that model per week, the red line is the Artificial Analysis Intelligence index [https://artificialanalysis.ai/] of the model sorted from highest to lowest. At this moment, DeepSeek V4 Flash and Qwen3.8 Flash are the best models to use for the majority of cases. GLM-5.3 -Flash is great for more demanding work.