in the loop

Baichuan1-7B
#266 of 274 scored.

BaichuanJun 1, 2023Open weights

Capabilities Index

Range 75.6–98.5

90.5

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

No independent scores yet.

Epoch AI hasn't run Baichuan1-7B yet. Its scores show up here the morning after they do.

Everything else Epoch has for it

  • PIQA52.4%
  • MMLU23.1%
  • BBH10.0%
  • GSM8K9.2%

On the index

Around it.

  1. #263Qwen-1_8BAlibaba92.9
  2. #264open_llama_7bMeta91.7
  3. #265Phi-1.5Microsoft91.5
  4. #266Baichuan1-7BBaichuan90.5
  5. #267RedPajama-INCITE-7B-BaseTogether90.4
  6. #268Dolly 2.0-12bDatabricks89.7
  7. #269DeepSeek Coder 6.7BDeepSeek89.6

Sources