New Finance Agent Benchmark Released
openai/gpt-4.1-2025-04-14 GPT 4.1

Released Date: 4/14/2025

Avg. Accuracy:

69.1%

Latency:

32.62s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

FinanceAgent

24.6%

( 9 / 24 )

CorpFin

71.2%

( 1 / 39 )

CaseLaw

85.8%

( 4 / 62 )

ContractLaw

68.4%

( 20 / 69 )

TaxEval

78.4%

( 6 / 49 )

MortgageTax

79.0%

( 3 / 29 )

Math500

87.2%

( 19 / 45 )

AIME

39.8%

( 17 / 39 )

MGSM

87.2%

( 31 / 43 )

LegalBench

81.9%

( 6 / 67 )

MedQA

91.2%

( 10 / 47 )

GPQA

64.6%

( 18 / 40 )

MMLU Pro

80.5%

( 10 / 40 )

LiveCodeBench

50.1%

( 15 / 40 )

MMMU

68.9%

( 14 / 26 )

SWE-bench

47.4%

( 3 / 10 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$2.00 / M Tokens

Output Cost

$8.00 / M Tokens

Input Cost (per char)

N/A

Output Cost (per char)

$2.19 / M chars

Join our mailing list to receive benchmark updates on

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