New Finance Agent Benchmark Released
openai/gpt-5-2025-08-07 GPT 5

Current flagship model from OpenAI.

Released Date: 8/7/2025

Avg. Accuracy:

75.4%

Latency:

477.76s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

FinanceAgent

46.9%

( 3 / 39 )

CorpFin

73.5%

( 1 / 52 )

CaseLaw

74.9%

( 5 / 35 )

TaxEval

78.3%

( 8 / 69 )

MortgageTax

76.8%

( 9 / 41 )

Math500

96.0%

( 2 / 54 )

AIME

93.4%

( 1 / 59 )

MGSM

92.8%

( 7 / 62 )

LegalBench

84.5%

( 1 / 84 )

MedQA

96.3%

( 2 / 65 )

GPQA

85.6%

( 2 / 61 )

MMLU Pro

87.0%

( 3 / 59 )

MMMU

81.5%

( 1 / 38 )

LiveCodeBench

77.1%

( 10 / 58 )

IOI

20.0%

( 2 / 18 )

Terminal-Bench

48.8%

( 2 / 20 )

SWE-bench

68.8%

( 2 / 21 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$1.25 / M Tokens

Output Cost

$10.00 / 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.