New Finance Agent Benchmark Released

Released date

Model

Last Updated 8/5/2025

anthropic/claude-opus-4-1-20250805

Claude Opus 4.1 (Nonthinking)

Released Date: 8/5/2025

Avg. Accuracy:

74.1%

Latency:

29.24s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

46.1%

( 2 / 30 )

46.1%

2 / 30

80.9%

( 31 / 71 )

80.9%

31 / 71

66.5%

( 35 / 74 )

66.5%

35 / 74

75.9%

( 14 / 58 )

75.9%

14 / 58

65.2%

( 24 / 35 )

65.2%

24 / 35

93.0%

( 13 / 54 )

93.0%

13 / 54

44.2%

( 22 / 48 )

44.2%

22 / 48

94.2%

( 2 / 51 )

94.2%

2 / 51

81.9%

( 9 / 73 )

81.9%

9 / 73

92.5%

( 10 / 51 )

92.5%

10 / 51

69.9%

( 17 / 50 )

69.9%

17 / 50

87.8%

( 1 / 48 )

87.8%

1 / 48

64.6%

( 16 / 49 )

64.6%

16 / 49

74.0%

( 11 / 32 )

74.0%

11 / 32

Academic Benchmarks

Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$15.00 / M Tokens

Output Cost

$75.00 / M Tokens

Input Cost (per char)

N/A

Output Cost (per char)

$19.91 / M chars

Join our mailing list to receive benchmark updates on

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