Slopalytics Launches AI Benchmark, Usage Dashboard

Slopalytics is a useful bridge between lab scores and developer behavior, but it should complement—not replace—benchmarks.

• –Compares model intelligence against cost, task time, token usage, and total spend
• –T3 Code data shows which models and coding harnesses developers actually use
• –Usage metrics reveal adoption patterns that standard evaluations miss
• –Results remain sensitive to task mix, pricing assumptions, defaults, and incomplete reporting
• –Its long-term value depends on adding stronger agentic coding and end-to-end workflow evaluations