New Finance Agent Benchmark Released

Anthropic's most powerful model.

Released Date: 5/22/2025

Avg. Accuracy:

73.8%

Latency:

20.95s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

FinanceAgent

42.3%

( 7 / 29 )

CaseLaw

81.5%

( 22 / 63 )

ContractLaw

68.8%

( 15 / 69 )

TaxEval

75.8%

( 13 / 50 )

MortgageTax

70.9%

( 18 / 30 )

Math500

90.4%

( 14 / 46 )

AIME

41.3%

( 17 / 40 )

MGSM

93.8%

( 1 / 44 )

LegalBench

81.7%

( 10 / 68 )

MedQA

92.9%

( 7 / 48 )

GPQA

71.7%

( 12 / 41 )

MMLU Pro

86.1%

( 1 / 41 )

LiveCodeBench

62.6%

( 11 / 41 )

MMMU

73.4%

( 8 / 27 )

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)

$27.05 / M chars

Join our mailing list to receive benchmark updates on

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