Private AI
GLM-5.2 with thinking enabled for harder long-horizon coding, autonomous agent workflows, complex engineering optimization, and real-world development tasks.
Added Jun 15, 2026
Model weightsContext Window
1.0M
Max Output
131.1K
Input Price (Auto)
$0.44/1M
Output Price (Auto)
$1.39/1M
Cache Read (Auto)
$0.082/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
51.1
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Coding Index
68.8
Agentic Index
43.1
GPQA Diamond
Graduate-level scientific reasoning
89.5%
Better than 92% of models compared
HLE
Humanity's Last Exam
40.1%
Better than 96% of models compared
IFBench
Instruction-following benchmark
73.3%
Better than 91% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
99.1%
Better than 99% of models compared
AA-LCR
Long context reasoning evaluation
71.3%
Better than 95% of models compared
GDPval-AA
Economically valuable tasks
50.5%
CritPt
Research-level physics reasoning
20.9%
SciCode
Python programming for scientific computing
50.5%
Better than 93% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
50.8%
AA-Omniscience Accuracy
Proportion of correctly answered questions
25.1%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
28.1%
Last updated Jul 26, 2026
Artificial AnalysisBetter than 95% of models compared
