readable AI benchmarks

Z AI

GLM-5.3 (max)

reasoning · closed weights · Aug 18, 2026

Quality Score65.3
Value Score47.9
Reliability57.1
Cache Discount81%

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$1.40
Output
$4.40
Cached Input
$0.260
Cached Output
not available
Cost per task
$0.683

Capability

Intelligence
59.5
Coding
74.8
Agentic
59.1
Omniscience
14.3
Correct
33.9%
Blended price
$0.902

Answer outcomes

Correct 33.9%Incorrect 19.6%Abstained 46.6%

Artificial Analysis benchmarks

GDPval-AA v2
63%
τ³-Banking
50%
Terminal-Bench v2.1
84%
SciCode
56%
Humanity’s Last Exam
42%
GPQA Diamond
92%
CritPt
19%
AA-Omniscience
57%
AA-LCR
76%

Similar models