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:

59.2%

Latency:

11.41s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

3.6%

( 21 / 24 )

3.6%

21 / 24

57.6%

( 20 / 39 )

57.6%

20 / 39

76.1%

( 40 / 62 )

76.1%

40 / 62

63.3%

( 50 / 69 )

63.3%

50 / 69

69.3%

( 31 / 49 )

69.3%

31 / 49

72.7%

( 12 / 29 )

72.7%

12 / 29

85.2%

( 21 / 45 )

85.2%

21 / 45

25.2%

( 22 / 39 )

25.2%

22 / 39

92.5%

( 8 / 43 )

92.5%

8 / 43

77.2%

( 33 / 67 )

77.2%

33 / 67

43.3%

( 47 / 47 )

43.3%

47 / 47

67.7%

( 13 / 40 )

67.7%

13 / 40

79.4%

( 15 / 40 )

79.4%

15 / 40

43.1%

( 21 / 40 )

43.1%

21 / 40

72.6%

( 8 / 26 )

72.6%

8 / 26

18.4%

( 9 / 10 )

18.4%

9 / 10

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)

$0.15 / M chars

Output Cost (per char)

$0.21 / M chars

Join our mailing list to receive benchmark updates on

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