New Finance Agent Benchmark Released

Latest version of the Mistral Small model.

Released Date: 9/17/2024

Avg. Accuracy:

54.0%

Latency:

5.62s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

CaseLaw

73.5%

( 48 / 63 )

ContractLaw

64.1%

( 44 / 69 )

TaxEval

54.1%

( 45 / 49 )

Math500

70.6%

( 39 / 46 )

AIME

5.6%

( 36 / 40 )

MGSM

85.0%

( 39 / 44 )

MedQA

57.0%

( 41 / 48 )

GPQA

50.8%

( 26 / 41 )

MMLU Pro

64.4%

( 34 / 40 )

LiveCodeBench

15.3%

( 40 / 41 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.20 / M Tokens

Output Cost

$0.60 / M Tokens

Input Cost (per char)

$0.06 / M chars

Output Cost (per char)

$0.18 / M chars

Join our mailing list to receive benchmark updates on

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