Accuracy (Average)

59.10%

Latency (Average)

256.74s

Avg. Cost (In/Out)

3 / 15

Context Window

200k

Max Output Tokens

64k

Input Modality

Hyperparameter settings
Default Provider : Anthropic

Temperature

1

Top P

Default

Top K

Default

Max Output Tokens

64,000

Benchmarks

Accuracy

Rankings

0.0%

± 0.98
56/ 94

0.0%

± 1.91
34/ 48

0.0%

± 1.93
35/ 48

0.0%

± 0.96
26/ 66

0.0%

± 3.27
29/ 46

0.0%

± 0.90
58/ 101

0.0%

± 0.97
68/ 93

0.0%

± 2.31
59/ 96

0.0%

± 2.10
30/ 50

0.0%

± 1.17
67/ 102

0.0%

± 0.41
25/ 114

0.0%

± 0.27
46/ 95

0.0%

± 0.37
56/ 94

0.0%

± 1.07
35/ 63
Contact us
Or send us an email at contact@vals.ai
Proprietary Benchmarks (contact us to get access)
Academic Benchmarks

Read about our methodology.