DeepSeek V4 Flash 0731

Release Date: 7/31/2026

Vals Index

Accuracy (Vals Index)

63.95% ± 1.31

Latency (Vals Index)

859.57s

Cost/Test (Vals Index)

$0.06

Context Window

1M

Max Output Tokens

384k

Input Modality

Hyperparameter settings
Default Provider : DeepSeek

Temperature

1

Top P

Default

Top K

Default

Max Output Tokens

384,000

Reasoning Effort

high

Show rankings only among open weight models

Benchmarks

Accuracy

Rankings

0.0%

± 1.31
14/ 42

0.0%

± 0.96
48/ 128

0.0%

± 2.15
33/ 77

0.0%

± 1.97
32/ 77

0.0%

± 0.90
79/ 133

0.0%

± 1.69
21/ 127

0.0%

± 0.97
11/ 132

0.0%

± 0.50
92/ 130

0.0%

± 0.34
39/ 126

0.0%

± 1.35
18/ 47
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.