in the loop

internlm-7b
#246 of 274 scored.

Shanghai AI LabJul 5, 2023

Capabilities Index

Range 90.8–109.5

102.9

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

No independent scores yet.

Epoch AI hasn't run internlm-7b yet. Its scores show up here the morning after they do.

Everything else Epoch has for it

  • LAMBADA67.0%
  • HellaSwag60.8%
  • ARC AI259.3%
  • PIQA55.8%
  • MMLU34.7%
  • GSM8K31.2%
  • BBH16.0%

On the index

Around it.

  1. #243Falcon-40BTII104.5
  2. #244Baichuan2-13BBaichuan103.2
  3. #245Qwen2.5-Coder (1.5B)Alibaba103.0
  4. #246internlm-7bShanghai AI Lab102.9
  5. #247Llama 3.2 1BMeta102.0
  6. #248INTELLECT-1Prime Intellect100.9
  7. #249MPT-30BDatabricks100.7

Sources