in the loop

Mistral 7B v0.1
#222 of 274 scored.

MistralSep 27, 2023Open weights

Capabilities Index

Range 102.4–116.3

112.2

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

No independent scores yet.

Epoch AI hasn't run Mistral 7B v0.1 yet. Its scores show up here the morning after they do.

Everything else Epoch has for it

  • TriviaQA75.2%
  • HellaSwag74.7%
  • OpenBookQA73.1%
  • ARC AI271.5%
  • PIQA66.0%
  • GSM8K54.4%
  • Winogrande50.6%
  • MMLU50.0%
  • BBH41.5%
  • ANLI20.6%

On the index

Around it.

  1. #219GPT-3.5 Turbo (Jun 2023)OpenAI113.4
  2. #220Qwen2.5-Coder (7B)Alibaba113.1
  3. #221Qwen-14BAlibaba113.0
  4. #222Mistral 7B v0.1Mistral112.2
  5. #223Falcon-180BTII112.1
  6. #224internlm-20bShanghai AI Lab112.1
  7. #225Gemma 7BGoogle112.0

Sources