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)

Thinking version of the Opus 4.1 model.

Released Date: 8/5/2025

Avg. Accuracy:

76.9%

Latency:

62.21s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

50.9%

( 1 / 39 )

50.9%

1 / 39

72.4%

( 12 / 35 )

72.4%

12 / 35

77.2%

( 10 / 69 )

77.2%

10 / 69

53.4%

( 38 / 41 )

53.4%

38 / 41

95.4%

( 3 / 54 )

95.4%

3 / 54

78.2%

( 15 / 59 )

78.2%

15 / 59

94.4%

( 1 / 62 )

94.4%

1 / 62

93.6%

( 7 / 65 )

93.6%

7 / 65

75.5%

( 12 / 61 )

75.5%

12 / 61

87.6%

( 2 / 59 )

87.6%

2 / 59

77.5%

( 8 / 38 )

77.5%

8 / 38

66.5%

( 20 / 58 )

66.5%

20 / 58

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)

N/A

Join our mailing list to receive benchmark updates on

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