in the loop

Qwen-14B
#221 of 274 scored.

AlibabaSep 24, 2023Open weights

Capabilities Index

Range 103.3–117.4

113.0

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

No independent scores yet.

Epoch AI hasn't run Qwen-14B yet. Its scores show up here the morning after they do.

Everything else Epoch has for it

  • ARC AI279.2%
  • LAMBADA71.1%
  • GSM8K61.3%
  • PIQA59.8%
  • MMLU55.1%
  • BBH40.0%

On the index

Around it.

  1. #218Llama 2-70BMeta113.8
  2. #219GPT-3.5 Turbo (Jun 2023)OpenAI113.4
  3. #220Qwen2.5-Coder (7B)Alibaba113.1
  4. #221Qwen-14BAlibaba113.0
  5. #222Mistral 7B v0.1Mistral112.2
  6. #223Falcon-180BTII112.1
  7. #224internlm-20bShanghai AI Lab112.1

Sources