New Finance Agent Benchmark Released

Released date

Model

Last Updated 8/7/2025

openai/gpt-5-nano-2025-08-07

Cheapest and fastest model in the GPT-5 family.

Released Date: 8/7/2025

Avg. Accuracy:

74.4%

Latency:

51.57s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

63.3%

( 23 / 26 )

63.3%

23 / 26

72.8%

( 32 / 60 )

72.8%

32 / 60

64.9%

( 25 / 35 )

64.9%

25 / 35

93.8%

( 12 / 54 )

93.8%

12 / 54

83.3%

( 12 / 50 )

83.3%

12 / 50

89.3%

( 33 / 53 )

89.3%

33 / 53

49.4%

( 71 / 75 )

49.4%

71 / 75

93.2%

( 8 / 56 )

93.2%

8 / 56

59.6%

( 28 / 52 )

59.6%

28 / 52

77.9%

( 25 / 50 )

77.9%

25 / 50

70.9%

( 17 / 32 )

70.9%

17 / 32

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.05 / M Tokens

Output Cost

$0.40 / M Tokens

Input Cost (per char)

$0.01 / M chars

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.