Its interesting to notice that here https://metr.org/blog/2025-03-19-measuring-ai-ability-to-com... we default to measuring LLM coding performance as how long[~5h] a human task a model can complete with 50% success-rate (with 80% fall back for the second chart [~.5h]), while here it seems that for actual coding we really care about the last 90-100% of the costly model's performance.