GLM-5.2 is the leading open weights model on Artificial Analysis' Intelligence Index, scoring 51, only behind Fable 5's 60, Opus 4.8's 56, and GPT-5.5's 55

Z ai's GLM-5.2 just became the highest-scoring open-weight model on the Artificial Analysis Intelligence Index. It pulled a 51 — not bad for a model you can actually download and run.

The only models sitting above it are all proprietary heavyweights: Fable 5 at 60, Opus 4.8 at 56, and GPT-5.5 at 55. That's elite company for an open-weight contender.

Perhaps more interesting than the raw score is GLM-5.2's position on the Pareto frontier for intelligence versus cost per task. Translation: it's delivering top-tier performance without burning a hole in your inference budget. No other open model currently matches that balance.

For teams building on open models, this reshuffles the deck. The gap between open and closed is narrowing — and GLM-5.2 is doing the heavy lifting.