GLM 5.1

Release Date: 4/1/2026

Vals Index

Accuracy (Vals Index)

52.45% ± 1.61

Latency (Vals Index)

899.50s

Cost/Test (Vals Index)

$0.86

Context Window

200k

Max Output Tokens

131k

Input Modality

Hyperparameter settings
Default Provider : Zhipu AI

Temperature

1

Top P

0.95

Top K

Default

Max Output Tokens

131,072

Show rankings only among open weight models

Benchmarks

Accuracy

Rankings

0.0%

± 1.61
13/ 30

0.0%

± 4.09
11/ 23

0.0%

± 0.94
26/ 116

0.0%

± 0.61
11/ 28

0.0%

± 3.12
7/ 13

0.0%

± 2.12
24/ 68

0.0%

± 2.06
50/ 65

0.0%

± 4.18
14/ 42

0.0%

± 1.26
5/ 12

0.0%

± 0.90
62/ 122

0.0%

± 4.55
30/ 66

0.0%

± 1.82
31/ 116

0.0%

± 1.06
44/ 122

0.0%

± 0.43
17/ 119

0.0%

± 0.33
23/ 115

0.0%

± 0.00
11/ 24

0.0%

± 1.90
19/ 64

0.0%

± 1.35
17/ 35
Contact us
Or send us an email at contact@vals.ai

License type:

Proprietary (contact us to get access)
Industry Partner
Academic

Read our methodology.