New Finance Agent Benchmark Released

Released date

Model

Last Updated 4/17/2025

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

Gemini 2.5 Flash Preview (Thinking)

Gemini 2.5 Flash Preview (Thinking)

Released Date: 4/17/2025

Avg. Accuracy:

74.7%

Latency:

25.71s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

82.5%

( 21 / 73 )

82.5%

21 / 73

60.6%

( 66 / 76 )

60.6%

66 / 76

74.4%

( 24 / 60 )

74.4%

24 / 60

69.5%

( 20 / 35 )

69.5%

20 / 35

91.8%

( 15 / 54 )

91.8%

15 / 54

90.0%

( 30 / 53 )

90.0%

30 / 53

81.8%

( 10 / 75 )

81.8%

10 / 75

91.0%

( 15 / 53 )

91.0%

15 / 53

58.6%

( 30 / 52 )

58.6%

30 / 52

46.9%

( 32 / 51 )

46.9%

32 / 51

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.15 / M Tokens

Output Cost

$3.50 / M Tokens

Input Cost (per char)

$0.04 / 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.