New Finance Agent Benchmark Released

Gemini 1.5 Flash, 002 model.

Released Date: 9/24/2024

Avg. Accuracy:

55.0%

Latency:

8.48s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

CorpFin

46.6%

( 39 / 44 )

TaxEval

53.4%

( 57 / 60 )

MortgageTax

54.6%

( 32 / 35 )

Math500

78.8%

( 35 / 54 )

AIME

17.3%

( 36 / 50 )

MGSM

86.6%

( 41 / 53 )

LegalBench

62.0%

( 62 / 75 )

GPQA

46.0%

( 40 / 52 )

MMLU Pro

65.5%

( 42 / 50 )

MMMU

57.2%

( 28 / 32 )

LiveCodeBench

36.9%

( 43 / 52 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.07 / M Tokens

Output Cost

$0.30 / M Tokens

Input Cost (per char)

$0.02 / M chars

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.