Benchmark Almanac

Z.ai

Best on the Capabilities Index GLM-5.3 157.1
31 models 19 model cards read z.ai

How does Z.ai stack up?

Every model on Epoch AI's Capabilities Index by release date, with Z.ai's in color.

50 100 150 2023 2024 2025 2026 2027 GLM-5.3-Flash GLM-5 50 100 150 2023 2024 2025 2026 2027 GLM-5.3-Flash GLM-4.7

Source: Epoch Capabilities Index, Epoch AI (CC BY 4.0)

Z.ai's best models

Z.ai Aug 2026

GLM-5.3

Open weights Flagship

157.1 #32 of 256
Epoch Capabilities Index
Self-Reported Index 161.5 #23 of 404
  • DeepSWE 69% #7 /28
  • NL2Repo-Bench 58% #8 /30
  • Terminal-Bench 4.0 41.8% #12 /40
Z.ai Aug 2026

GLM-5.3-Flash

Open weights

153.8 #52 of 256
Epoch Capabilities Index
Self-Reported Index 158.8 #39 of 404
  • DeepSWE 63.4% #13 /28
  • NL2Repo-Bench 56.3% #10 /30
  • Terminal-Bench 4.0 36.7% #18 /40
Z.ai Jun 2026

GLM-5.2

Open weights Flagship

153.0 #54 of 256
Epoch Capabilities Index
Self-Reported Index 154.4 #64 of 404
  • SWE-bench Verified 78.7% #5 /32
  • DeepSWE 43.8% #24 /28
  • AutomationBench 7.76% #30 /42
Z.ai Apr 2026

GLM-5.1

Open weights Flagship

150.7 #68 of 256
Epoch Capabilities Index
Self-Reported Index 153.6 #70 of 404
  • SWE-bench Verified 74.2% #16 /32
  • AutomationBench 6.20% #31 /42
  • NL2Repo-Bench 42.7% #20 /30
Z.ai Feb 2026

GLM-5

Open weights Flagship

146.5 #88 of 256
Epoch Capabilities Index
Self-Reported Index 147.9 #108 of 404
  • SWE-bench Verified 72.1% #22 /32
  • IFBench 72% #34 /80
  • Terminal-Bench 2.0 52.4% #16 /43
Z.ai Dec 2025

GLM-4.7

Open weights Flagship

143.3 #106 of 256
Epoch Capabilities Index
Self-Reported Index 148.0 #106 of 404
  • Terminal-Bench 2.0 33.4% #30 /43
  • Toolathlon 23.8% #37 /50
  • GPQA Diamond 83.3% #87 /229

What benchmarks does Z.ai mention most?

Here are the 28 benchmarks Z.ai mentions most in its launch posts.

Source: Labs’ launch posts, read by Benchmark Almanac

Model cards

DateModelDocumentBenchmarks
Oct 12, 2026 GLM-5.3-FlashX-Legal GLM-5.3-FlashX-Legal (official documentation) 1
Aug 26, 2026 GLM-5.3-Flash GLM-5.3-Flash: Frontier Intelligence, Flash Cost (blog) 18
Aug 14, 2026 GLM-5.3 GLM-5.3 model card (Hugging Face) 16
Jun 16, 2026 GLM-5.2 GLM-5.2 model card (Hugging Face) 17
Apr 7, 2026 GLM-5.1 GLM-5.1 model card (Hugging Face) 16
Apr 1, 2026 GLM-5V-Turbo GLM-5V-Turbo (official documentation) 19
Feb 11, 2026 GLM-5 GLM-5 model card (Hugging Face) 15
Jan 30, 2026 GLM-OCR GLM-OCR model card (Hugging Face) 2
Jan 19, 2026 glm-4.7-flash GLM-4.7-Flash model card (Hugging Face) 7
Jan 14, 2026 GLM-Image GLM-Image (official blog) 5
Dec 22, 2025 GLM-4.7 GLM-4.7 model card (Hugging Face) 15
Dec 8, 2025 GLM-4.6V GLM-4.6V blog and model card 32
Sep 30, 2025 GLM-4.6 GLM-4.6 launch blog (Z.ai) and Hugging Face card, chart 'LLM Performance Evaluation: Agentic, Reasoning and Coding' 8
Aug 11, 2025 GLM-4.5V GLM-4.5V model card (Hugging Face) 40
Jul 28, 2025 GLM-4.5 GLM-4.5: Reasoning, Coding, and Agentic Abilities (Z.ai launch blog) 13
Jul 1, 2025 GLM-4.1V-9B-Thinking GLM-4.1V-9B-Thinking model card and technical report 26
Apr 14, 2025 GLM-Z1-32B-0414 GLM-4-0414 model series README (GitHub) 10
Jan 16, 2024 GLM-4 GLM-4 launch at Zhipu DevDay (official announcement text and slides, reposted on Volcengine developer community) 10
Oct 27, 2023 ChatGLM3-6B ChatGLM3 GitHub README, base-model evaluation table 8

Every Z.ai model