Accuracy (Average)

69.20%

Latency (Average)

52.53s

Avg. Cost (In/Out)

15 / 75

Context Window

200k

Max Output Tokens

32k

Input Modality

Hyperparameter settings
Default Provider : Anthropic

Temperature

1

Top P

Default

Top K

Default

Max Output Tokens

32,000

Benchmarks

Accuracy

Rankings

0.0%

± 2.07
14/ 50

0.0%

± 1.96
32/ 50

0.0%

± 0.99
48/ 68

0.0%

± 3.19
40/ 48

0.0%

± 0.86
23/ 103

0.0%

± 1.63
47/ 95

0.0%

± 2.16
43/ 98

0.0%

± 1.13
58/ 102

0.0%

± 0.22
22/ 95

0.0%

± 0.33
5/ 96

0.0%

± 1.00
25/ 65
Contact us
Or send us an email at contact@vals.ai
Proprietary Benchmarks (contact us to get access)
Academic Benchmarks

Read about our methodology.