Benchmark

Zhipu GLM — reported benchmarks

Zhipu AI (Z.ai) · source page ↗ · last checked Aug 22, 2026, 12:04 PM

Reported benchmarks · GLM-5.2

captured Aug 22, 2026, 12:04 PM
BenchmarkScore
SWE-bench Pro62.1%
Terminal-Bench 2.181.0%
GPQA Diamond91.2%
AIME 202699.2%
HLE54.7% · with tools

Vendor-reported via automated web search — not independently verified. See the cited matrix on /models.

Change history