New Finance Agent Benchmark Released
openai/o3-2025-04-16 o3

Released Date: 4/16/2025

Avg. Accuracy:

78.6%

Latency:

85.67s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

FinanceAgent

48.3%

( 1 / 29 )

CorpFin

71.0%

( 3 / 40 )

CaseLaw

82.8%

( 19 / 63 )

ContractLaw

66.0%

( 36 / 69 )

TaxEval

79.0%

( 1 / 50 )

MortgageTax

78.4%

( 5 / 30 )

Math500

94.6%

( 3 / 46 )

AIME

85.3%

( 4 / 40 )

MGSM

91.4%

( 15 / 44 )

LegalBench

82.5%

( 4 / 68 )

MedQA

96.1%

( 2 / 48 )

GPQA

83.6%

( 2 / 41 )

MMLU Pro

85.6%

( 2 / 41 )

LiveCodeBench

83.9%

( 1 / 41 )

MMMU

80.1%

( 2 / 27 )

SWE-bench

49.8%

( 3 / 12 )

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)

N/A

Join our mailing list to receive benchmark updates on

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