Logo
together/meta-llama/Llama-2-70b-hf Llama 2 (70B)

Llama 2 Reference Model, 70B parameters with FP16 quantization.

Released Date: 7/18/2023

Avg. Accuracy:

59.5%

Latency:

7.23s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

LegalBench

59.4%

( 34 / 43 )

ContractLaw

59.7%

( 40 / 47 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.90 / M Tokens

Output Cost

$0.90 / M Tokens

Input Cost (per char)

$0.00 / M chars

Output Cost (per char)

$0.04 / M chars

Join our mailing list to receive benchmark updates on

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