New Finance Agent Benchmark Released

Released date

Model

Last Updated 4/17/2025

google/gemini-2.5-flash-preview-04-17

Gemini 2.5 Flash Preview (Nonthinking)

Gemini 2.5 Flash Preview (Nonthinking)

Released Date: 4/17/2025

Avg. Accuracy:

73.4%

Latency:

8.57s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

62.6%

( 12 / 39 )

62.6%

12 / 39

81.5%

( 23 / 62 )

81.5%

23 / 62

63.4%

( 47 / 69 )

63.4%

47 / 69

75.4%

( 15 / 49 )

75.4%

15 / 49

70.9%

( 17 / 29 )

70.9%

17 / 29

91.6%

( 11 / 45 )

91.6%

11 / 45

89.8%

( 24 / 43 )

89.8%

24 / 43

82.8%

( 2 / 67 )

82.8%

2 / 67

86.7%

( 21 / 47 )

86.7%

21 / 47

53.3%

( 23 / 40 )

53.3%

23 / 40

49.6%

( 16 / 40 )

49.6%

16 / 40

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.15 / M Tokens

Output Cost

$0.60 / M Tokens

Input Cost (per char)

$0.04 / M chars

Output Cost (per char)

$0.15 / M chars

Join our mailing list to receive benchmark updates on

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