--- license: mit library_name: transformers pipeline_tag: text-generation tags: - mock - showcase - html-model-card --- # GLM-5.2 (mock model card) > [!NOTE] > **This is a mock repository.** It exists to showcase how far you can push a Hugging Face model card with sanitized inline-style HTML. The chart below is a pure-HTML recreation of the benchmark figure from the [zai-org/GLM-5.2](https://huggingface.co/zai-org/GLM-5.2) model card, using Hugging Face org avatars as the chart logos. All numbers are illustrative.
LLM Performance Evaluation
8 Benchmarks: SWE-bench Pro, Terminal-Bench 2.1 (Terminus), NL2Repo, DeepSWE, ProgramBench, MCP-Atlas, Tool-Decathlon, Humanity’s Last Exam
All models are evaluated under their maximum thinking effort
Z.ai
GLM-5.2GLM-5.1Claude Opus 4.8GPT-5.5Gemini 3.1 Pro
62.1
zai logo
58.4
zai logo
69.2
anthropic logo
58.6
openai logo
54.2
google logo
SWE-bench Pro
81.0
zai logo
63.5
zai logo
85.0
anthropic logo
84.0
openai logo
74.0
google logo
Terminal-Bench 2.1
48.9
zai logo
42.7
zai logo
69.7
anthropic logo
50.7
openai logo
33.4
google logo
NL2Repo
46.2
zai logo
18.0zai logo
58.0
anthropic logo
70.0
openai logo
10.0google logo
DeepSWE
63.7
zai logo
50.9
zai logo
71.9
anthropic logo
70.8
openai logo
39.5
google logo
ProgramBench
77.0
zai logo
71.8
zai logo
77.8
anthropic logo
75.3
openai logo
69.2
google logo
MCP-Atlas
48.2
zai logo
40.7
zai logo
59.9
anthropic logo
55.6
openai logo
48.8
google logo
Tool-Decathlon
54.7w/ Tools
40.5zai logo
52.3w/ Tools
31.0zai logo
57.9w/ Tools
49.8anthropic logo
52.2w/ Tools
41.4openai logo
51.4w/ Tools
45.0google logo
Humanity's Last Exam
## How this chart is built No images, no SVG, no JavaScript. The figure above is plain HTML with inline styles (flexbox columns for the bars, a CSS grid for the 4×2 chart layout, and `linear-gradient` fills), which is what the Hugging Face model-card sanitizer allows. The logos are the org avatars served from `cdn-avatars.huggingface.co`.