New Finance Agent Benchmark Released

Latest gpt-4o snapshot from November 20th, 2024.

Released Date: 11/20/2024

Avg. Accuracy:

67.0%

Latency:

10.44s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

CorpFin

56.6%

( 17 / 35 )

CaseLaw

82.9%

( 14 / 55 )

ContractLaw

68.0%

( 25 / 62 )

TaxEval

78.1%

( 7 / 42 )

MortgageTax

72.1%

( 13 / 23 )

Math500

74.0%

( 26 / 38 )

AIME

11.9%

( 26 / 34 )

MGSM

90.2%

( 17 / 36 )

LegalBench

79.8%

( 10 / 60 )

GPQA

53.0%

( 19 / 35 )

MMLU Pro

69.1%

( 25 / 35 )

MMMU

68.1%

( 12 / 22 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$2.50 / M Tokens

Output Cost

$10.00 / M Tokens

Input Cost (per char)

$0.63 / M chars

Output Cost (per char)

$2.71 / M chars

Join our mailing list to receive benchmark updates on

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