explainx / blog
GLM-5.2 vs Claude Fable 5 on Kilo Code planning benchmarks — near-tie at 1/10th the price. Comparison updated July 1 with Fable live again.
Jul 9, 2026
OpenAI launches GPT-5.6 publicly July 9; Fable 5 live globally since July 1. Sol Ultra leads Terminal-Bench at 91.9%; Fable leads SWE-Bench Pro at 80.3%. Terra matches Fable on terminal work at half the price — tier-by-tier guide.
Jun 15, 2026
The U.S. pulled Fable 5 on June 12. Within 48 hours, two Chinese labs had released models that beat it on key benchmarks — fully open source, at a fraction of the cost. Here is what GLM-5.2 is, what it can do, and what the timing means.
Jul 28, 2026
SlopCodeBench measures whether a model can maintain a codebase across incrementally revealed checkpoints, not just solve one problem once. humanlayer's dhorthy ran Claude Opus 5, Opus 4.8, and Sonnet 5 through 17 checkpoints and watched live for six hours. Opus 5 won on strict pass rate but also tripled the code volume — this post breaks down what the numbers mean and what HN argued about.
