readable AI benchmarks (simplified)

readable AI benchmarks

Z AI

GLM-5 (Reasoning)

reasoning · open weights · Feb 11, 2026

GLM-5 (Reasoning) has a Quality Score of 46.5, ranking 117th among 551 scored models. Per 1M tokens, pricing is $1.00 input, $3.20 output, and $0.200 cached input. It accepts text input, outputs text, and has a 200k token context window. Its Reliability Score is 50.1, ranking 111th among 553 scored models, above average (total average: 35.6). Its Value Score is 34.2, around average compared with the total Value average of 30.7.

Quality Score46.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score34.2
Factual reliability50.1
Cache Discount80%

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
200k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$1.00
Output
$3.20
Cached Input
$0.200
Cache write
not available
Cost per task
not available

Capability

Intelligence
27.9
Coding
not available
Agentic
not available
Omniscience
0.3
Correct
26.3%
Blended price
$0.660

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 52.3%

Correct 26.3%Incorrect 26.0%Partial / not attempted 47.7%

Artificial Analysis benchmarks

Humanity’s Last Exam
29%
GPQA Diamond
82%
CritPt
2%
AA-Omniscience
50%
AA-LCR
76%

Similar models

Support me! Patreon