ProgramBench now shows Pareto-frontier tradeoffs across models and cost

jyangballin · x · 2026-07-27

ProgramBench has added Pareto views to compare models on cost vs. score.

The screenshot shows the benchmark’s leaderboard-style breakdown and a scatter plot of models across different cost points. The author recommends using % resolved as the official metric, while % tests passed is kept only for illustration.

The main takeaway is that the benchmark now makes it easier to see which models sit on the Pareto frontier, not just which one tops a single score table.

Related event: ProgramBench Adds Pareto Curves to Track Rapid Model Progress(3 posts)→

Original post →

More from Models

Models channel →