AI Comparison

1 / 3
좌우로 스와이프하여 전환

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.

Author
Z.aiZ.ai
Release Date
2026-02-11
Knowledge Cutoff
2026-02-17
License
Open Model
I/O Format
Context Length
80K / 131K
API I/O (1M)
$0.72 / $2.3
How to Use
API Access
Output Speed
51 tok/s
Arena Overall
1456
Intelligence Index
49.8
Coding Index
44.2
Math Index
LiveBench
68.7
ForecastBench
60.1
GPQA Diamond
82.0%
HLE
27.2%
MMLU-Pro
AIME 2025
MATH-500
LB Reasoning
69.1
LB Math
83.5
LB Data Analysis
67.9
LiveCodeBench
LB Coding
73.6
LB Agentic
55.0
TAU2
98.2%
TerminalBench
43.2%
SciCode
46.2%
IFBench
72.3%
AA-LCR
0.6
Hallucination (HHEM)
Factual Consistency (HHEM)
LB Language
77.5
LB Instruction Following
55.3