New Finance Agent Benchmark Released

Released date

Model

Last Updated 4/5/2025

together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

Llama 4 Maverick

Llama 4 Maverick 17B 128E Instruct FP8

Released Date: 4/5/2025

Avg. Accuracy:

57.9%

Latency:

12.72s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

3.6%

( 30 / 33 )

3.6%

30 / 33

57.6%

( 25 / 44 )

57.6%

25 / 44

69.3%

( 38 / 60 )

69.3%

38 / 60

72.7%

( 14 / 35 )

72.7%

14 / 35

85.2%

( 29 / 54 )

85.2%

29 / 54

25.2%

( 32 / 50 )

25.2%

32 / 50

92.4%

( 11 / 53 )

92.4%

11 / 53

77.2%

( 39 / 75 )

77.2%

39 / 75

43.3%

( 56 / 56 )

43.3%

56 / 56

67.7%

( 20 / 52 )

67.7%

20 / 52

79.4%

( 20 / 50 )

79.4%

20 / 50

47.3%

( 31 / 51 )

47.3%

31 / 51

71.7%

( 15 / 32 )

71.7%

15 / 32

18.4%

( 12 / 13 )

18.4%

12 / 13

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.27 / M Tokens

Output Cost

$0.85 / M Tokens

Input Cost (per char)

$0.23 / M chars

Output Cost (per char)

$0.22 / M chars

Join our mailing list to receive benchmark updates on

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