New Finance Agent Benchmark Released

Released date

Model

Last Updated 9/5/2025

alibaba/qwen3-max-preview

Qwen 3 Max Preview

Largest and most Recent Qwen Model

Released Date: 9/5/2025

Avg. Accuracy:

67.1%

Latency:

162.45s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

17.7%

( 21 / 34 )

17.7%

21 / 34

56.8%

( 26 / 45 )

56.8%

26 / 45

65.3%

( 22 / 28 )

65.3%

22 / 28

77.2%

( 11 / 62 )

77.2%

11 / 62

60.7%

( 20 / 52 )

60.7%

20 / 52

92.4%

( 11 / 55 )

92.4%

11 / 55

78.9%

( 28 / 77 )

78.9%

28 / 77

87.4%

( 29 / 58 )

87.4%

29 / 58

77.8%

( 7 / 54 )

77.8%

7 / 54

80.2%

( 18 / 52 )

80.2%

18 / 52

66.9%

( 16 / 54 )

66.9%

16 / 54

44.4%

( 8 / 16 )

44.4%

8 / 16

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$1.20 / M Tokens

Output Cost

$6.00 / M Tokens

Input Cost (per char)

N/A

Output Cost (per char)

$1.81 / M chars

Join our mailing list to receive benchmark updates on

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