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:

60.1%

Latency:

7.82s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

53.9%

( 27 / 41 )

53.9%

27 / 41

74.4%

( 49 / 69 )

74.4%

49 / 69

61.8%

( 58 / 72 )

61.8%

58 / 72

59.0%

( 51 / 56 )

59.0%

51 / 56

71.7%

( 17 / 33 )

71.7%

17 / 33

79.2%

( 32 / 52 )

79.2%

32 / 52

19.0%

( 30 / 46 )

19.0%

30 / 46

88.0%

( 33 / 49 )

88.0%

33 / 49

71.8%

( 47 / 72 )

71.8%

47 / 72

50.9%

( 47 / 49 )

50.9%

47 / 49

44.4%

( 38 / 48 )

44.4%

38 / 48

69.6%

( 33 / 46 )

69.6%

33 / 46

38.5%

( 36 / 47 )

38.5%

36 / 47

58.8%

( 24 / 30 )

58.8%

24 / 30

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)

$0.05 / M chars

Output Cost (per char)

$0.15 / M chars

Join our mailing list to receive benchmark updates on

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