GPT 5.4

Release Date: 3/5/2026

Vals Index

Accuracy (Vals Index)

64.77% ± 1.95

Latency (Vals Index)

460.70s

Cost/Test (Vals Index)

$0.67

Context Window

1M

Max Output Tokens

128k

Input Modality

Hyperparameter settings
Default Provider : OpenAI

Temperature

Default

Top P

Default

Top K

Default

Max Output Tokens

128,000

Reasoning Effort

xhigh

Benchmarks

Accuracy

Rankings

0.0%

± 1.95
6/ 40

0.0%

± 1.52
5/ 28

0.0%

± 2.24
14/ 47

0.0%

± 0.94
12/ 97

0.0%

± 2.85
9/ 45

0.0%

± 2.15
21/ 51

0.0%

± 3.32
24/ 51

0.0%

± 0.91
8/ 69

0.0%

± 4.99
1/ 24

0.0%

± 3.12
18/ 49

0.0%

± 0.87
22/ 104

0.0%

± 4.84
2/ 26

0.0%

± 0.53
5/ 96

0.0%

± 1.91
4/ 99

0.0%

± 9.87
1/ 50

0.0%

± 1.04
16/ 103

0.0%

± 0.41
4/ 116

0.0%

± 0.18
5/ 95

0.0%

± 0.42
8/ 97

0.0%

± 0.79
4/ 66

0.0%

± 1.85
3/ 41

0.0%

± 5.25
8/ 52
Contact us
Or send us an email at contact@vals.ai
Proprietary Benchmarks (contact us to get access)
Academic Benchmarks

Read about our methodology.