readable AI benchmarks

Z AI

GLM-5.3-Flash

reasoning · closed weights · Aug 26, 2026

GLM-5.3-Flash has a Quality Score of 60.6, ranking 32nd among 260 scored models. Per 1M tokens, pricing is $0.150 input, $0.500 output, and $0.026 cached input. It accepts text input, outputs text, and has a 400k token context window. Its Reliability Score is 53.7, ranking 31st among 260 scored models, above average (total average: 33.2). Its Value Score is 56.8, high compared with the total Quality average of 26.8.

Quality Score60.6
Value Score56.8
Reliability53.7
Cache Discount83%

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
400k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.150
Output
$0.500
Cached Input
$0.026
Cached Output
not available
Cost per task
$0.087

Capability

Intelligence
57.5
Coding
71.5
Agentic
58.2
Omniscience
7.5
Correct
27.5%
Blended price
$0.098

Answer outcomes

Correct 27.5%Incorrect 20.0%Abstained 52.5%

Artificial Analysis benchmarks

GDPval-AA v2
63%
τ³-Banking
47%
Terminal-Bench v2.1
84%
SciCode
46%
Humanity’s Last Exam
40%
GPQA Diamond
91%
CritPt
15%
AA-Omniscience
54%
AA-LCR
78%

Similar models