GLM-5 benchmarks and performance, in charts
Every chart we tracked that shows GLM-5, from the lab itself and from the trackers people trust, with how far each one travelled. Includes GLM-5.2.
GLM-5 on its own benchmark table
Drawn from the numbers huggingface.co published as text (Benchmark, read Aug 11, 2026). Each panel is one test; the highlighted bar is GLM-5. Source: huggingface.co.
See the numbers
| HLE | Gemini 3 Pro 37.2, GPT-5.2 (xhigh) 35.4, Kimi K2.5 31.5, GLM-5 30.5, Claude Opus 4.5 28.4, DeepSeek-V3.2 25.1, GLM-4.7 24.8 |
|---|---|
| HLE (w/ Tools) | Kimi K2.5 51.8, GLM-5 50.4, Gemini 3 Pro 45.8, GPT-5.2 (xhigh) 45.5, Claude Opus 4.5 43.4, GLM-4.7 42.8, DeepSeek-V3.2 40.8 |
| AIME 2026 I | Claude Opus 4.5 93.3, GLM-4.7 92.9, GLM-5 92.7, DeepSeek-V3.2 92.7, Kimi K2.5 92.5, Gemini 3 Pro 90.6 |
| HMMT Nov. 2025 | GPT-5.2 (xhigh) 97.1, GLM-5 96.9, GLM-4.7 93.5, Gemini 3 Pro 93, Claude Opus 4.5 91.7, Kimi K2.5 91.1, DeepSeek-V3.2 90.2 |
| IMOAnswerBench | GPT-5.2 (xhigh) 86.3, Gemini 3 Pro 83.3, GLM-5 82.5, GLM-4.7 82, Kimi K2.5 81.8, Claude Opus 4.5 78.5, DeepSeek-V3.2 78.3 |
| GPQA-Diamond | GPT-5.2 (xhigh) 92.4, Gemini 3 Pro 91.9, Kimi K2.5 87.6, Claude Opus 4.5 87, GLM-5 86, GLM-4.7 85.7, DeepSeek-V3.2 82.4 |
Official charts from Z.ai
As published on X, Hugging Face, GitHub and their blog. Each card opens our own page for the chart.
From benchmark trackers and others
More charts that feature GLM-5
Benchmark trackers, other labs and researchers. Each card opens our own page for the chart.
Free with your email
See all 67 GLM-5 charts
Every official launch chart and independent benchmark we found for GLM-5, with who posted each one. Plus Monday's email: the week's charts that beat their usual likes.
Unlocks all 35 giants. One email a week, leave any time. What you get · Log in
More charts that feature GLM-5 more
%201_1fqgOj.webp?dpl=6accf0d261fecbe6ba702f4d)
Make it yours
Your numbers, in a look-alike of the original.
Starts from the real numbers of "LLM Performance Bench 3.0" by Z.ai. Replace every number with yours before you post. Make one like this, step by step
Look-alike score 9.2 of 10. Free pictures carry a small "Made with ViralChart" line. That line is how other people find us.
Questions people ask
How does GLM-5 perform?
We hold 10 charts that show GLM-5 (including GLM-5.2), posted between Mar 2026 and Aug 2026. The most seen is "GLM-5.1 Code Arena Ranking" by Arena with 494,078 views.
GLM-5 vs Kimi K2: which is better?
4 charts put them side by side. Which wins depends on the benchmark; each chart shows its own test and who published it.
Who publishes GLM-5 benchmark charts?
Arena, Artificial Analysis, NVIDIA, Clouded Judgement (Jamin Ball), Z.ai, @ArtificialAnlys, @arena, @EpochAIResearch, @Kimi_Moonshot, @Alibaba_Qwen