New Finance Agent Benchmark Released

Anthropic's latest-generation workhorse model, offering a balance of performance and speed.

Released Date: 5/22/2025

Avg. Accuracy:

67.0%

Latency:

255.29s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

FinanceAgent

43.5%

( 8 / 33 )

CorpFin

59.9%

( 21 / 44 )

CaseLaw

74.0%

( 7 / 27 )

TaxEval

73.5%

( 29 / 61 )

MortgageTax

74.6%

( 13 / 35 )

Math500

90.3%

( 22 / 55 )

AIME

38.5%

( 29 / 51 )

MGSM

93.0%

( 5 / 54 )

LegalBench

81.5%

( 15 / 76 )

MedQA

90.3%

( 21 / 57 )

GPQA

69.4%

( 20 / 53 )

MMLU Pro

79.4%

( 20 / 51 )

MMMU

72.4%

( 14 / 32 )

LiveCodeBench

59.7%

( 24 / 53 )

IOI

6.5%

( 5 / 12 )

SWE-bench

65.0%

( 2 / 15 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$3.00 / M Tokens

Output Cost

$15.00 / M Tokens

Input Cost (per char)

N/A

Output Cost (per char)

$6.73 / M chars

Join our mailing list to receive benchmark updates on

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