name = "GLM-5.2"
description = "Open flagship GLM for long-horizon coding agents and million-token context work"
family = "glm"
release_date = "2026-06-13"
last_updated = "2026-06-13"
attachment = false
reasoning = true
temperature = true
tool_call = true
structured_output = true
open_weights = true

[limit]
context = 1_000_000
output = 131_072

[modalities]
input = ["text"]
output = ["text"]

[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/zai-org/GLM-5.2"

[[benchmarks]]
name = "SWE-Bench Pro"
score = 62.1
metric = "resolve rate"
source = "https://z.ai/blog/glm-5.2"
date = "2026-06-16"

[[benchmarks]]
name = "Terminal-Bench"
score = 82.7
metric = "success rate"
harness = "Claude Code"
version = "2.1"
source = "https://z.ai/blog/glm-5.2"
date = "2026-06-16"

[[benchmarks]]
name = "FrontierSWE"
score = 74.4
metric = "dominance"
source = "https://z.ai/blog/glm-5.2"
date = "2026-06-16"