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:

74.7%

Latency:

21.58s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

60.9%

( 11 / 35 )

60.9%

11 / 35

86.2%

( 2 / 55 )

86.2%

2 / 55

64.7%

( 39 / 62 )

64.7%

39 / 62

75.2%

( 13 / 42 )

75.2%

13 / 42

88.6%

( 10 / 38 )

88.6%

10 / 38

52.2%

( 10 / 34 )

52.2%

10 / 34

92.0%

( 9 / 36 )

92.0%

9 / 36

79.9%

( 9 / 60 )

79.9%

9 / 60

82.0%

( 20 / 40 )

82.0%

20 / 40

61.1%

( 15 / 35 )

61.1%

15 / 35

78.9%

( 12 / 35 )

78.9%

12 / 35

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)

$0.29 / M chars

Output Cost (per char)

$0.35 / M chars

Join our mailing list to receive benchmark updates on

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