New Finance Agent Benchmark Released

Released date

Model

Last Updated 4/9/2025

grok/grok-3-beta

Released Date: 4/9/2025

Avg. Accuracy:

73.6%

Latency:

19.60s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

24.1%

( 8 / 22 )

24.1%

8 / 22

69.1%

( 4 / 38 )

69.1%

4 / 38

88.1%

( 1 / 60 )

88.1%

1 / 60

63.5%

( 44 / 67 )

63.5%

44 / 67

78.8%

( 2 / 47 )

78.8%

2 / 47

89.8%

( 13 / 43 )

89.8%

13 / 43

58.7%

( 10 / 37 )

58.7%

10 / 37

91.3%

( 15 / 41 )

91.3%

15 / 41

82.0%

( 5 / 65 )

82.0%

5 / 65

83.9%

( 22 / 45 )

83.9%

22 / 45

73.7%

( 7 / 38 )

73.7%

7 / 38

79.9%

( 11 / 38 )

79.9%

11 / 38

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$3.00 / M Tokens

Output Cost

$15.00 / M Tokens

Input Cost (per char)

$1.37 / M chars

Output Cost (per char)

$3.47 / M chars

Join our mailing list to receive benchmark updates on

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