New Finance Agent Benchmark Released

Released date

Model

Last Updated 8/5/2025

anthropic/claude-opus-4-1-20250805-thinking

Claude Opus 4.1 (Thinking)

Released Date: 8/5/2025

Avg. Accuracy:

79.0%

Latency:

46.97s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

82.4%

( 22 / 71 )

82.4%

22 / 71

66.2%

( 37 / 74 )

66.2%

37 / 74

77.2%

( 10 / 58 )

77.2%

10 / 58

53.4%

( 33 / 35 )

53.4%

33 / 35

95.4%

( 3 / 54 )

95.4%

3 / 54

78.2%

( 11 / 48 )

78.2%

11 / 48

94.8%

( 1 / 51 )

94.8%

1 / 51

93.6%

( 5 / 51 )

93.6%

5 / 51

75.5%

( 7 / 50 )

75.5%

7 / 50

87.6%

( 2 / 48 )

87.6%

2 / 48

66.5%

( 13 / 49 )

66.5%

13 / 49

77.5%

( 6 / 32 )

77.5%

6 / 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)

$4.88 / 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.