Zhipu AI

glm-4.6

mitMultimodal
Benchmark Average (0–100)
61.0%
Average of non-null benchmark scores across all evaluated tasks.

BENCHMARK SCORES

GPQA81.0%

Graduate-Level Google-Proof Q&A. PhD-level multiple-choice questions in chemistry, biology, and physics. Scored by accuracy.

AIME 202593.9%

AIME 2025 is a mathematics competition benchmark testing advanced problem-solving.

SWE-bench Verified68.0%

SWE-bench Verified evaluates models on real-world software engineering tasks from GitHub issues.

BrowseComp45.1%

BrowseComp tests web browsing comprehension, measuring ability to find and synthesize information from websites.

HLE17.2%

Humanity's Last Exam (HLE) is a multi-modal benchmark testing frontier knowledge across mathematics, humanities, and natural sciences with 2,500 expert-level questions.

OTHER BENCHMARKS

Terminal Bench
40.5%

MODEL INFO

Organization
Zhipu AI
Context Window
131,072
Release Date
2025-09-30
Knowledge Cutoff
Parameters
357000000000.0B
License
mit
Input Price ($/M)
$0.5500
Output Price ($/M)
$2.1900

METADATA

Announcement Date
2025-09-30
Organization Country
CN
Canonical ID