GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, and performs complex coding tasks.
Author
Z.aiRelease Date
2026-04-01
Knowledge Cutoff
—
License
Proprietary
I/O Format
Context Length
203K / 131K
API I/O (1M)
$1.2 / $4
How to Use
—
Output Speed
23 tok/sArena Overall
—Intelligence Index
42.9Coding Index
36.2Math Index
—LiveBench
48.8ForecastBench
—GPQA Diamond
80.9%HLE
15.8%MMLU-Pro
—AIME 2025
—MATH-500
—LB Reasoning
56.1LB Math
70.4LB Data Analysis
54.1LiveCodeBench
—LB Coding
73.9LB Agentic
3.3TAU2
98.5%TerminalBench
32.6%SciCode
43.5%IFBench
61.1%AA-LCR
0.6Hallucination (HHEM)
—Factual Consistency (HHEM)
—LB Language
62.3LB Instruction Following
27.21 / 3
Swipe to compare
GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, and performs complex coding tasks.
Author
Z.aiRelease Date
2026-04-01
Knowledge Cutoff
—
License
Proprietary
I/O Format
Context Length
203K / 131K
API I/O (1M)
$1.2 / $4
How to Use
—
Output Speed
23 tok/sArena Overall
—Intelligence Index
42.9Coding Index
36.2Math Index
—LiveBench
48.8ForecastBench
—GPQA Diamond
80.9%HLE
15.8%MMLU-Pro
—AIME 2025
—MATH-500
—LB Reasoning
56.1LB Math
70.4LB Data Analysis
54.1LiveCodeBench
—LB Coding
73.9LB Agentic
3.3TAU2
98.5%TerminalBench
32.6%SciCode
43.5%IFBench
61.1%AA-LCR
0.6Hallucination (HHEM)
—Factual Consistency (HHEM)
—LB Language
62.3LB Instruction Following
27.2