GLM-5.2 Ranks Third on ProgramBench Leaderboard
Open-weight model GLM-5.2 has taken third place on the official ProgramBench leaderboard with an 8.5% score. As the first open-weight model evaluated, its performance sparked discussions, though some warn that average scores might be misleading.
2026-07-23 ~ 2026-07-23 · 3 related posts
- GLM-5.2 hits 8.5% on ProgramBench, ranks 3rd overall — parth007_96 · 2026-07-23
- GLM 5.2 reaches No. 3 on the official ProgramBench leaderboard — klieret · 2026-07-23
- GLM 5.2 ranks third on ProgramBench, but the thread warns averages can mislead — jyangballin · 2026-07-23