ProgramBench adds language heatmaps to model pages and per-task costs to its leaderboard
A user says five-minute Muse Code runs added a language heatmap to each model page and $/task to ProgramBench’s homepage leaderboard.
TLDR
ProgramBench says it evaluates whether language models can rebuild programs from scratch. A user says they used five-minute Muse Code runs to add language heatmaps to model pages and $/task to the homepage leaderboard, with more models coming soon.
Combined views
466
1 Source, first seen 1h ago
likes
