Latest version of the Mistral Large model.

Released Date: 11/18/2024

Avg. Accuracy:

63.7%

Latency:

9.41s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

CaseLaw

75.1%

( 31 / 50 )

ContractLaw

67.0%

( 25 / 57 )

TaxEval

67.7%

( 21 / 37 )

Math500

74.4%

( 20 / 33 )

AIME

9.6%

( 24 / 29 )

MGSM

88.2%

( 19 / 31 )

MedQA

76.2%

( 22 / 35 )

GPQA

45.2%

( 21 / 30 )

MMLU Pro

69.7%

( 19 / 30 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$2.00 / M Tokens

Output Cost

$6.00 / M Tokens

Input Cost (per char)

$0.58 / M chars

Output Cost (per char)

$1.95 / M chars

Join our mailing list to receive benchmark updates on

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