readable AI benchmarks

Z AI

GLM-5.2 (Non-reasoning)

non-reasoning · open weights · Jun 16, 2026

Quality Score39.3
Value Score28.0
Reliability46.7
Cache Discount81%

Model specification

Reasoning
non-reasoning
Input modalities
text
Output modalities
text
Context window
1M tokens
Weights
open weights

Token prices USD per 1M tokens

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

Capability

Intelligence
34.8
Coding
46.5
Agentic
35.1
Omniscience
-6.6
Correct
20.3%
Blended price
$0.902

Answer outcomes

Correct 20.3%Incorrect 26.9%Abstained 52.9%

Artificial Analysis benchmarks

GDPval-AA v2
45%
τ³-Banking
17%
Terminal-Bench v2.1
52%
SciCode
36%
Humanity’s Last Exam
10%
GPQA Diamond
69%
CritPt
3%
AA-Omniscience
47%
AA-LCR
45%

Similar models