New Finance Agent Benchmark Released

Released date

Model

Last Updated 8/5/2025

anthropic/claude-opus-4-1-20250805

Claude Opus 4.1 (Nonthinking)

State of the art coding model from Anthropic.

Released Date: 8/5/2025

Avg. Accuracy:

69.7%

Latency:

467.00s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

46.1%

( 4 / 39 )

46.1%

4 / 39

71.1%

( 14 / 35 )

71.1%

14 / 35

75.9%

( 18 / 69 )

75.9%

18 / 69

65.2%

( 26 / 41 )

65.2%

26 / 41

93.0%

( 13 / 54 )

93.0%

13 / 54

44.2%

( 30 / 59 )

44.2%

30 / 59

94.2%

( 2 / 62 )

94.2%

2 / 62

81.9%

( 9 / 84 )

81.9%

9 / 84

92.5%

( 13 / 65 )

92.5%

13 / 65

70.0%

( 24 / 61 )

70.0%

24 / 61

87.8%

( 1 / 59 )

87.8%

1 / 59

74.0%

( 14 / 38 )

74.0%

14 / 38

64.6%

( 23 / 58 )

64.6%

23 / 58

15.2%

( 5 / 18 )

15.2%

5 / 18

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)

$27.27 / M chars

Join our mailing list to receive benchmark updates on

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