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:

72.6%

Latency:

23.38s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

42.3%

( 10 / 33 )

42.3%

10 / 33

75.8%

( 18 / 61 )

75.8%

18 / 61

59.0%

( 29 / 35 )

59.0%

29 / 35

90.4%

( 20 / 55 )

90.4%

20 / 55

41.3%

( 27 / 51 )

41.3%

27 / 51

93.8%

( 3 / 54 )

93.8%

3 / 54

81.7%

( 12 / 76 )

81.7%

12 / 76

92.9%

( 11 / 57 )

92.9%

11 / 57

71.7%

( 15 / 53 )

71.7%

15 / 53

86.1%

( 4 / 51 )

86.1%

4 / 51

73.3%

( 12 / 32 )

73.3%

12 / 32

62.6%

( 20 / 53 )

62.6%

20 / 53

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)

$28.66 / M chars

Join our mailing list to receive benchmark updates on

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