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:

73.9%

Latency:

21.93s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

60.9%

( 15 / 41 )

60.9%

15 / 41

86.2%

( 2 / 69 )

86.2%

2 / 69

64.7%

( 45 / 72 )

64.7%

45 / 72

75.2%

( 18 / 56 )

75.2%

18 / 56

88.6%

( 22 / 52 )

88.6%

22 / 52

52.2%

( 18 / 46 )

52.2%

18 / 46

91.7%

( 15 / 49 )

91.7%

15 / 49

79.9%

( 18 / 72 )

79.9%

18 / 72

82.0%

( 28 / 49 )

82.0%

28 / 49

61.1%

( 23 / 48 )

61.1%

23 / 48

78.9%

( 19 / 46 )

78.9%

19 / 46

65.5%

( 14 / 47 )

65.5%

14 / 47

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)

$0.31 / M chars

Output Cost (per char)

$0.34 / M chars

Join our mailing list to receive benchmark updates on

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