in the loop

XGen-7B
#262 of 274 scored.

SalesforceJun 27, 2023Open weights

Capabilities Index

Range 78.8–100.8

93.4

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

No independent scores yet.

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

Everything else Epoch has for it

  • HellaSwag65.6%
  • PIQA51.0%
  • Winogrande29.8%
  • ARC AI221.6%
  • OpenBookQA20.3%
  • MMLU15.1%

On the index

Around it.

  1. #259MPT-7BDatabricks94.6
  2. #260Gemma 2BGoogle94.2
  3. #261StarCoder 2 7BHugging Face93.6
  4. #262XGen-7BSalesforce93.4
  5. #263Qwen-1_8BAlibaba92.9
  6. #264open_llama_7bMeta91.7
  7. #265Phi-1.5Microsoft91.5

Sources