Llama 3.3 Instruct Turbo, 70B parameters with FP16 quantization.

Released Date: 12/6/2024

Avg. Accuracy:

65.1%

Latency:

7.63s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

CaseLaw

76.6%

( 24 / 43 )

ContractLaw

66.0%

( 30 / 50 )

TaxEval

63.9%

( 21 / 30 )

Math500

73.4%

( 17 / 26 )

AIME

16.9%

( 11 / 22 )

MGSM

91.3%

( 8 / 24 )

LegalBench

78.0%

( 15 / 48 )

GPQA

50.0%

( 12 / 23 )

MMLU Pro

69.9%

( 14 / 24 )

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)

$0.24 / 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.