GLM 4.5

zai-org · released 2025-07-25 · mit license

GLM-4.5 is Z.ai's 355B-parameter (32B active) MoE (July 2025, MIT); per its technical report it scores 64.2% SWE-bench Verified, 91.0% AIME 24, 79.1% GPQA and 84.6% MMLU-Pro. A top-3 open model at release.

Key specs

TypeLocal open-weight
Parameters358.34B total · MoE, — active
Architectureglm4_moe
Context window131K tokens
Knowledge cutoff2024-12-31
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond79.1%
SWE-bench Verified64.2%
AIME91%
MMLU-Pro84.6%
BFCL v3 (tool use)
Composite score6.57
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M209.3 GB207.8 GB131K

Strengths & weaknesses

Strengths: Strong agentic/tool-use on par with Claude Sonnet 4 at release; Excellent math (AIME 91.0, MATH-500 98.2); MIT license

Weaknesses: Coding (SWE-bench 64.2) below top proprietary of its era; Superseded by GLM-4.6 and GLM-5