Z.AI releases GLM-5.2: first open-source model with solid 1M-token context, built for long-horizon coding tasks

GLM-5.2: Built for Long-Horizon Tasks

Z.AI open-sourced GLM-5.2, a model built for long-horizon coding tasks. It delivers a genuinely usable 1M-token context—not just accepting more tokens, but maintaining quality across long agent trajectories. IndexShare reuses one indexer across every four sparse attention layers, cutting per-token FLOPs by 2.9× at 1M context; MTP acceptance length improved by up to 20%. On FrontierSWE it beats GPT-5.5 by 1%, and on PostTrainBench it outranks both GPT-5.5 and Opus 4.7, placing second. It's the top open-source model across all three long-horizon coding benchmarks. MIT license, no regional restrictions.

Why it matters: Z.AI open-sources GLM-5.2 with a 1M-token context window and two new architectural components, explicitly targeting long-horizon agent tasks. Domestic flagship model release gets full weight per policy, but the body excerpt lacks full benchmarks, capping it below 85.