AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

GLM-5.2

Zhipu AI·

LLMsopen-weightcloud + localFrontier

Overview

753B Mixture-of-Experts (~40B active) open-weight model under MIT license. Introduces the IndexShare attention mechanism (~2.9x lower per-token FLOPs at 1M-token context) and a usable 1M-token context window. Ships with two thinking-effort levels; the highest tier is marketed as 'Max'. Available as open weights on Hugging Face and via the Z.ai API. Vendor-reported benchmarks (maximum thinking effort): GPQA Diamond 91.2, SWE-bench Pro 62.1, Terminal-Bench 2.1 81.0, HLE 40.5 (no tools).

Capabilities and innovations

753B total / ~40B active MoE1M-token contextTwo thinking-effort levels (incl. 'Max')Agentic / long-horizon codingMIT licenseIndexShare attention (~2.9x FLOP reduction at 1M-token context)Usable 1M-token context window

Benchmarks

BenchmarkScoreSource
GPQA Diamond85.61%vendor
Z.ai self-report: GPQA Diamond 91,2%. Not used as primary value (deviation >3 points from the independent runs).
Humanity’s Last Exam (no tools)40.5%vendor
HLE 40.5 no-tools (recorded for cross-model comparability). Z.ai also reports 54.7 with tools, which is not comparable to the no-tools HLE used here.
SWE-bench Pro62.1%vendor
SWE-bench Pro 62.1 — Z.ai-reported (maximum thinking effort).
MMLU-Pro86.71%unsourced
Terminal-Bench 2.x77.9%vendor
Terminal-Bench 2.1 (Terminus-2) 81.0 — Z.ai-reported; Z.ai also lists 82.7 on its best-reported harness. Not used as primary value (deviation >3 points from the non-vendor measurement).
Terminal-Bench 3.04.6%vendor
Terminal-Bench 3.0 4.6 — Z.ai-reported in the GLM-5.3 launch comparison table. Figures taken from launch coverage on 2026-08-17; the primary table at docs.z.ai was not reachable from the build environment for direct verification. Do not compare against the terminal_bench column: 3.0 is a harder generation on a different scale.
  • MMMU-Pro: not reported by the vendor

Architecture and hardware

Parameters
753B total, 40B active per token (MoE)
Estimated VRAM at Q4
~433 GB, Frontier class

Links

    More from Zhipu AI

    Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.