readable AI benchmarks (simplified)

readable AI benchmarks

Z AI

GLM-4.6 (Reasoning)

reasoning · open weights · Sep 30, 2025

GLM-4.6 (Reasoning) has a Quality Score of 28.8, ranking 260th among 551 scored models. Per 1M tokens, pricing is $0.550 input, $2.20 output, and $0.110 cached input. It has a 200k token context window. Its Reliability Score is 29.1, ranking 316th among 553 scored models, below average (total average: 35.6). Its Value Score is 22.4, low compared with the total Value average of 30.7.

Quality Score28.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score22.4
Factual reliability29.1
Cache Discount80%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
200k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.550
Output
$2.20
Cached Input
$0.110
Cache write
not available
Cost per task
not available

Capability

Intelligence
18.5
Coding
not available
Agentic
not available
Omniscience
-41.9
Correct
26.9%
Blended price
$0.407

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 95.6%

Correct 26.9%Incorrect 68.8%Partial / not attempted 4.4%

Artificial Analysis benchmarks

GDPval-AA v2
12%
τ³-Banking
13%
Humanity’s Last Exam
14%
GPQA Diamond
78%
CritPt
1%
AA-Omniscience
29%
AA-LCR
54%

Similar models

Support me! Patreon