Llama 3.1 Instruct Turbo, 70B parameters with FP8 quantization.

Released Date: 7/23/2024

Avg. Accuracy:

68.8%

Latency:

5.87s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

CorpFin

47.2%

( 17 / 24 )

CaseLaw

77.1%

( 22 / 43 )

ContractLaw

68.6%

( 14 / 50 )

TaxEval

61.1%

( 25 / 30 )

Math500

65.0%

( 22 / 26 )

LegalBench

78.2%

( 13 / 48 )

MedQA

84.8%

( 10 / 28 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.88 / M Tokens

Output Cost

$0.88 / M Tokens

Input Cost (per char)

$0.21 / M chars

Output Cost (per char)

$0.26 / M chars

Join our mailing list to receive benchmark updates on

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