Logo
together/togethercomputer/llama-2-13b Llama 2 (13B)

Llama 2 Reference Model, 13B parameters with FP16 quantization.

Released Date: 7/18/2023

Avg. Accuracy:

53.8%

Latency:

1.41s

Performance by Benchmark

Benchmarks

Accuracy

Rankings

LegalBench

51.6%

( 37 / 43 )

ContractLaw

55.9%

( 45 / 47 )

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Cost Analysis

Input Cost

$0.20 / M Tokens

Output Cost

$0.20 / M Tokens

Input Cost (per char)

$0.00 / M chars

Output Cost (per char)

$0.01 / M chars

Join our mailing list to receive benchmark updates on

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