New Finance Agent Benchmark Released

Released date

Model

Last Updated 4/5/2025

together/meta-llama/Llama-4-Scout-17B-16E-Instruct

Llama 4 Scout 17B 16E Instruct FP8

Released Date: 4/5/2025

Avg. Accuracy:

62.3%

Latency:

7.13s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

53.9%

( 24 / 38 )

53.9%

24 / 38

74.4%

( 42 / 60 )

74.4%

42 / 60

61.8%

( 54 / 67 )

61.8%

54 / 67

59.0%

( 42 / 47 )

59.0%

42 / 47

71.7%

( 14 / 26 )

71.7%

14 / 26

79.2%

( 24 / 43 )

79.2%

24 / 43

19.0%

( 22 / 37 )

19.0%

22 / 37

87.8%

( 28 / 41 )

87.8%

28 / 41

71.8%

( 41 / 65 )

71.8%

41 / 65

50.9%

( 43 / 45 )

50.9%

43 / 45

44.4%

( 29 / 38 )

44.4%

29 / 38

69.6%

( 27 / 38 )

69.6%

27 / 38

66.5%

( 15 / 24 )

66.5%

15 / 24

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.18 / M Tokens

Output Cost

$0.59 / M Tokens

Input Cost (per char)

$0.04 / M chars

Output Cost (per char)

$0.16 / M chars

Join our mailing list to receive benchmark updates on

Stay up to date as new benchmarks and models are released.