#65
ZA
GLM 4.5 Air
Zhipu AI
55.1 LLMBoard
Zhipu AI model product
GLM-4.6 is the latest version of Z.ai's flagship model, bringing significant improvements over GLM-4.5. Key features include: 200K token context window (expanded from 128K), superior coding performance with better real-world application in Claude Code/Cline/Roo Code/Kilo Code, advanced reasoning with tool use during inference, stronger agent capabilities, and refined writing aligned with human preferences. GLM-4.6 achieves competitive performance with DeepSeek-V3.2-Exp and Claude Sonnet 4, reaching near parity with Claude Sonnet 4 (48.6% win rate) on CC-Bench real-world coding tasks.
Updated Aug 10, 2026. Default version: GLM-4.6
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
No published version under this unique model currently has enough benchmark coverage to calculate a score.
Published benchmark records for the scored version currently unavailable.
No published benchmark result is linked to the scored version.
Preference and agent-evaluation signals from published Arena datasets.
| text factuality | industry medicine and healthcare | 20 | 1497.0 | 856 | N/A | |
| text factuality | chinese | 24 | 1510.9 | 820 | N/A | |
| text factuality | polish | 35 | 1412.6 | 611 | N/A | |
| text factuality | industry mathematical | 36 | 1450.0 | 810 | N/A | |
| text | german | 39 | 1449.6 | 642 | N/A | |
| text factuality | industry legal and government | 39 | 1468.4 | 1,052 | N/A | |
| text | polish | 41 | 1445.3 | 1,227 | N/A | |
| text | chinese | 42 | 1500.2 | 1,646 | N/A | |
| text | industry medicine and healthcare | 42 | 1458.6 | 1,879 | N/A | |
| text factuality | math | 43 | 1441.8 | 914 | N/A | |
| text | french | 46 | 1461.5 | 637 | N/A | |
| text | industry life and physical and social science | 48 | 1457.8 | 5,847 | N/A | |
| text | industry legal and government | 52 | 1449.9 | 2,398 | N/A | |
| text factuality | industry life and physical and social science | 53 | 1469.3 | 2,704 | N/A | |
| text factuality | english | 55 | 1459.3 | 12,989 | N/A | |
| text | exclude ties | 57 | 1437.7 | 24,984 | N/A | |
| text | industry mathematical | 57 | 1447.5 | 1,673 | N/A | |
| text factuality | overall | 57 | 1447.7 | 28,435 | N/A | |
| text factuality | exclude ties | 57 | 1448.9 | 19,686 | N/A | |
| text | overall | 58 | 1440.4 | 35,589 | N/A | |
| text | industry entertainment and sports and media | 58 | 1408.6 | 6,565 | N/A | |
| text | creative writing | 59 | 1412.8 | 5,064 | N/A | |
| text | english | 59 | 1448.2 | 17,175 | N/A | |
| text factuality | russian | 60 | 1444.7 | 1,286 | N/A | |
| text | non english | 63 | 1427.6 | 18,366 | N/A | |
| text factuality | creative writing | 64 | 1417.6 | 2,330 | N/A | |
| text factuality | industry entertainment and sports and media | 64 | 1412.4 | 3,071 | N/A | |
| text | japanese | 66 | 1392.5 | 310 | N/A | |
| text factuality | non english | 66 | 1433.2 | 14,288 | N/A | |
| text | industry writing and literature and language | 67 | 1415.1 | 7,935 | N/A | |
| text | spanish | 67 | 1435.4 | 880 | N/A | |
| text | industry software and it services | 69 | 1456.1 | 12,592 | N/A | |
| text factuality | expert | 69 | 1457.7 | 840 | N/A | |
| text factuality | hard prompts | 70 | 1464.1 | 14,772 | N/A | |
| text | korean | 71 | 1385.7 | 570 | N/A | |
| text factuality | industry software and it services | 72 | 1477.7 | 6,981 | N/A | |
| text | hard prompts | 74 | 1440.6 | 19,062 | N/A | |
| text style control | chinese | 74 | 1481.3 | 1,646 | N/A | |
| text | math | 75 | 1433.3 | 2,104 | N/A | |
| text factuality | hard prompts english | 77 | 1469.7 | 4,820 | N/A | |
| text factuality | industry business and management and financial operations | 77 | 1439.4 | 3,276 | N/A | |
| text factuality | industry writing and literature and language | 77 | 1418.3 | 3,891 | N/A | |
| text factuality | multi turn | 77 | 1440.7 | 2,797 | N/A | |
| text | coding | 80 | 1449.5 | 7,469 | N/A | |
| text | hard prompts english | 80 | 1443.8 | 9,595 | N/A | |
| text factuality | coding | 81 | 1482.3 | 3,564 | N/A | |
| text style control | german | 81 | 1430.5 | 642 | N/A | |
| webdev | webdev-html | 81 | 1349.4 | 6,543 | N/A | |
| text | instruction following | 82 | 1411.8 | 9,995 | N/A | |
| webdev | overall | 82 | 1339.0 | 6,569 | N/A | |
| webdev | webdev | 82 | 1339.0 | 6,569 | N/A | |
| text style control | industry mathematical | 83 | 1439.7 | 1,673 | N/A | |
| text | russian | 84 | 1419.3 | 2,758 | N/A | |
| text | longer query | 85 | 1423.4 | 8,730 | N/A | |
| text | industry business and management and financial operations | 87 | 1418.1 | 6,833 | N/A | |
| text | multi turn | 87 | 1426.7 | 5,666 | N/A | |
| text factuality | instruction following | 87 | 1422.7 | 5,089 | N/A | |
| text factuality | longer query | 88 | 1441.2 | 4,547 | N/A | |
| text style control | creative writing | 88 | 1402.0 | 5,064 | N/A | |
| text | expert | 89 | 1433.9 | 1,865 | N/A | |
| text style control | french | 89 | 1446.8 | 637 | N/A | |
| text style control | industry medicine and healthcare | 89 | 1450.3 | 1,879 | N/A | |
| text style control | japanese | 91 | 1374.4 | 310 | N/A | |
| text style control | polish | 93 | 1417.0 | 1,227 | N/A | |
| text style control | industry legal and government | 94 | 1436.6 | 2,398 | N/A | |
| text style control | spanish | 96 | 1413.6 | 880 | N/A | |
| text style control | exclude ties | 97 | 1416.6 | 24,984 | N/A | |
| text style control | industry writing and literature and language | 97 | 1404.9 | 7,935 | N/A | |
| text style control | industry life and physical and social science | 98 | 1446.8 | 5,847 | N/A | |
| text style control | overall | 99 | 1425.0 | 35,589 | N/A | |
| text style control | industry entertainment and sports and media | 99 | 1394.7 | 6,565 | N/A | |
| text style control | non english | 99 | 1409.1 | 18,366 | N/A | |
| text style control | english | 100 | 1436.3 | 17,175 | N/A | |
| text style control | korean | 100 | 1364.4 | 570 | N/A | |
| text style control | math | 102 | 1420.5 | 2,104 | N/A | |
| text style control | instruction following | 103 | 1414.9 | 9,995 | N/A | |
| text style control | longer query | 103 | 1432.5 | 8,730 | N/A | |
| text style control | hard prompts | 104 | 1442.1 | 19,062 | N/A | |
| text style control | hard prompts english | 105 | 1447.9 | 9,595 | N/A | |
| text style control | expert | 106 | 1440.7 | 1,865 | N/A | |
| text style control | russian | 106 | 1409.6 | 2,758 | N/A | |
| text style control | multi turn | 108 | 1421.1 | 5,666 | N/A | |
| text style control | industry software and it services | 110 | 1453.7 | 12,592 | N/A | |
| text style control | industry business and management and financial operations | 115 | 1412.9 | 6,833 | N/A | |
| text style control | coding | 120 | 1459.0 | 7,469 | N/A |
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
| iFlow | glm-4.6 | global | N/A | N/A | 200K | |
| 302.AI | glm-4.6 | global | $0.286 | $1.14 | 204.8K | |
| Helicone | glm-4.6 | global | $0.45 | $1.5 | 204.8K | |
| LLM Gateway | glm-4.6 | global | $0.55 | $2.2 | 204.8K | |
| OpenCode Zen | glm-4.6 | global | $0.60 | $2.2 | 204.8K | |
| Z.AI | glm-4.6 | global | $0.60 | $2.2 | 204.8K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| GLM-4.6 | N/A | 357B | 204.8K | 131.1K | Yes | MIT |
A concise description based on the published model registry.
GLM-4.6 is the latest version of Z.ai's flagship model, bringing significant improvements over GLM-4.5. Key features include: 200K token context window (expanded from 128K), superior coding performance with better real-world application in Claude Code/Cline/Roo Code/Kilo Code, advanced reasoning with tool use during inference, stronger agent capabilities, and refined writing aligned with human preferences. GLM-4.6 achieves competitive performance with DeepSeek-V3.2-Exp and Claude Sonnet 4, reaching near parity with Claude Sonnet 4 (48.6% win rate) on CC-Bench real-world coding tasks.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about GLM 4.6.
GLM 4.6's default version was released on Sep 30, 2025.
No official standard PAYG price is currently available for GLM 4.6. The lowest tracked third-party offer starts at $0.286 input and $1.14 output via 302.AI.
GLM 4.6 is published under Zhipu AI in the model registry.
The default version has a 204.8K token context window.
Yes. The default version is marked as open weight under MIT.
6 published provider offerings are linked to the default version.
No nearby ranked alternatives are currently available.