New Finance Agent Benchmark Released

Gemini 2.0 Flash, 001 model.

Released Date: 2/5/2025

Avg. Accuracy:

62.7%

Latency:

10.29s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

FinanceAgent

13.2%

( 23 / 33 )

CorpFin

38.5%

( 43 / 44 )

CaseLaw

73.7%

( 55 / 73 )

ContractLaw

66.8%

( 31 / 76 )

TaxEval

70.3%

( 37 / 60 )

MortgageTax

72.6%

( 15 / 35 )

Math500

88.0%

( 25 / 54 )

AIME

29.8%

( 29 / 50 )

MGSM

89.0%

( 35 / 53 )

LegalBench

79.7%

( 21 / 75 )

GPQA

65.2%

( 24 / 52 )

MMLU Pro

77.4%

( 26 / 50 )

LiveCodeBench

43.6%

( 34 / 51 )

MMMU

69.8%

( 19 / 32 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.10 / M Tokens

Output Cost

$0.40 / M Tokens

Input Cost (per char)

N/A

Output Cost (per char)

$0.12 / M chars

Join our mailing list to receive benchmark updates on

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