New Finance Agent Benchmark Released

Released date

Model

Last Updated 5/22/2025

anthropic/claude-opus-4-20250514

Claude Opus 4 (Nonthinking)

Anthropic's most powerful model.

Released Date: 5/22/2025

Avg. Accuracy:

77.4%

Latency:

13.78s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

81.5%

( 22 / 62 )

81.5%

22 / 62

68.8%

( 16 / 69 )

68.8%

16 / 69

75.8%

( 13 / 49 )

75.8%

13 / 49

70.9%

( 18 / 29 )

70.9%

18 / 29

90.4%

( 13 / 45 )

90.4%

13 / 45

41.2%

( 16 / 39 )

41.2%

16 / 39

93.8%

( 1 / 43 )

93.8%

1 / 43

81.7%

( 8 / 67 )

81.7%

8 / 67

92.9%

( 7 / 47 )

92.9%

7 / 47

71.7%

( 11 / 40 )

71.7%

11 / 40

86.1%

( 1 / 40 )

86.1%

1 / 40

73.4%

( 7 / 26 )

73.4%

7 / 26

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)

$4.16 / M chars

Output Cost (per char)

$29.40 / M chars

Join our mailing list to receive benchmark updates on

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