GLM-5.2 Benchmark Scores Spike Suspiciously
teortaxesTex · x · 2026-07-18
An X user pointed out Y-axis data anomalies in CAISI's benchmark leaderboard. They observed that while GLM-4 previously scored around 800, GLM-5.2's score recently jumped to roughly 1200, with other models also seeing a general score inflation. This suggests the organizers may have secretly altered the benchmark mix. The cited tweet claims GLM-5.2's cybersecurity capabilities are on par with Opus 4.6, and its overall level matches GPT 5.2.
More from Models
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11