GLM-5.1 benchmarks and performance, in charts
Every chart we tracked that shows GLM-5.1, from the lab itself and from the trackers people trust, with how far each one travelled.
GLM-5.1 on its own benchmark table
Drawn from the numbers huggingface.co published as text (Benchmark, read May 13, 2026). Each panel is one test; the highlighted bar is GLM-5.1. Source: huggingface.co.
See the numbers
| HLE | Gemini 3.1 Pro 45, GPT-5.4 39.8, Claude Opus 4.6 36.7, Kimi K2.5 31.5, GLM-5.1 31, GLM-5 30.5, Qwen3.6-Plus 28.8, Minimax M2.7 28, DeepSeek-V3.2 25.1 |
|---|---|
| HLE (w/ Tools) | Claude Opus 4.6 53.1, GLM-5.1 52.3, GPT-5.4 52.1, Kimi K2.5 51.8, Gemini 3.1 Pro 51.4, Qwen3.6-Plus 50.6, GLM-5 50.4, DeepSeek-V3.2 40.8 |
| AIME 2026 | GPT-5.4 98.7, Gemini 3.1 Pro 98.2, Claude Opus 4.6 95.6, GLM-5 95.4, GLM-5.1 95.3, Qwen3.6-Plus 95.1, DeepSeek-V3.2 95.1, Kimi K2.5 94.5, Minimax M2.7 89.8 |
| HMMT Nov. 2025 | GLM-5 96.9, Claude Opus 4.6 96.3, GPT-5.4 95.8, Gemini 3.1 Pro 94.8, Qwen3.6-Plus 94.6, GLM-5.1 94, Kimi K2.5 91.1, DeepSeek-V3.2 90.2, Minimax M2.7 81 |
| HMMT Feb. 2026 | GPT-5.4 91.8, Qwen3.6-Plus 87.8, Gemini 3.1 Pro 87.3, Claude Opus 4.6 84.3, GLM-5 82.8, GLM-5.1 82.6, Kimi K2.5 81.3, DeepSeek-V3.2 79.9, Minimax M2.7 72.7 |
| IMOAnswerBench | GPT-5.4 91.4, GLM-5.1 83.8, Qwen3.6-Plus 83.8, GLM-5 82.5, Kimi K2.5 81.8, Gemini 3.1 Pro 81, DeepSeek-V3.2 78.3, Claude Opus 4.6 75.3, Minimax M2.7 66.3 |
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-5.1
Benchmark trackers, other labs and researchers. Each card opens our own page for the chart.
Make it yours
Your numbers, in a look-alike of the original.
Starts from the real numbers of "Coding Performance SWE-Bench Pro Evaluation" by Z.ai. Replace every number with yours before you post. Make one like this, step by step
Look-alike score 7.7 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-5.1 perform?
We hold 6 charts that show GLM-5.1, posted between Apr 2026 and Apr 2026. The most seen is "GLM-5.1 Code Arena Ranking" by Arena with 494,078 views.
GLM-5.1 vs GLM-5: 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-5.1 benchmark charts?
Arena, Artificial Analysis, Z.ai, @Alibaba_Qwen, @arena