New Finance Agent Benchmark Released

Released date

Model

Last Updated 9/19/2025

grok/grok-4-fast-reasoning

Grok 4 Fast (Reasoning)

Released Date: 9/19/2025

Avg. Accuracy:

67.8%

Latency:

121.40s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

54.7%

( 1 / 36 )

54.7%

1 / 36

73.3%

( 3 / 47 )

73.3%

3 / 47

71.4%

( 13 / 30 )

71.4%

13 / 30

68.2%

( 42 / 64 )

68.2%

42 / 64

55.1%

( 31 / 37 )

55.1%

31 / 37

91.2%

( 3 / 54 )

91.2%

3 / 54

90.9%

( 27 / 57 )

90.9%

27 / 57

81.7%

( 13 / 79 )

81.7%

13 / 79

92.1%

( 16 / 60 )

92.1%

16 / 60

85.1%

( 3 / 56 )

85.1%

3 / 56

79.7%

( 21 / 54 )

79.7%

21 / 54

72.8%

( 13 / 34 )

72.8%

13 / 34

79.0%

( 8 / 56 )

79.0%

8 / 56

11.5%

( 5 / 16 )

11.5%

5 / 16

26.3%

( 10 / 15 )

26.3%

10 / 15

52.4%

( 5 / 17 )

52.4%

5 / 17

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.20 / M Tokens

Output Cost

$0.50 / M Tokens

Input Cost (per char)

N/A

Output Cost (per char)

N/A

Join our mailing list to receive benchmark updates on

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