New Finance Agent Benchmark Released

Released date

Model

Last Updated 3/24/2025

fireworks/deepseek-v3-0324

DeepSeek V3 (03/24/2025)

Released Date: 3/24/2025

Avg. Accuracy:

67.6%

Latency:

36.18s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

60.9%

( 18 / 45 )

60.9%

18 / 45

73.6%

( 9 / 28 )

73.6%

9 / 28

75.2%

( 23 / 62 )

75.2%

23 / 62

88.6%

( 24 / 54 )

88.6%

24 / 54

52.2%

( 23 / 52 )

52.2%

23 / 52

91.7%

( 19 / 55 )

91.7%

19 / 55

79.9%

( 19 / 77 )

79.9%

19 / 77

82.0%

( 37 / 58 )

82.0%

37 / 58

61.1%

( 28 / 54 )

61.1%

28 / 54

78.9%

( 24 / 52 )

78.9%

24 / 52

65.5%

( 19 / 54 )

65.5%

19 / 54

1.7%

( 12 / 14 )

1.7%

12 / 14

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$1.20 / M Tokens

Output Cost

$1.20 / M Tokens

Input Cost (per char)

$0.44 / M chars

Output Cost (per char)

$0.48 / M chars

Join our mailing list to receive benchmark updates on

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