in the loop

INTELLECT-1
#248 of 274 scored.

Prime IntellectNov 29, 2024

Capabilities Index

Range 88.5–106.3

100.9

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

No independent scores yet.

Epoch AI hasn't run INTELLECT-1 yet. Its scores show up here the morning after they do.

Everything else Epoch has for it

  • HellaSwag61.9%
  • ARC AI239.4%
  • GSM8K38.6%
  • MMLU33.2%
  • Winogrande31.6%
  • BBH13.1%

On the index

Around it.

  1. #245Qwen2.5-Coder (1.5B)Alibaba103.0
  2. #246internlm-7bShanghai AI Lab102.9
  3. #247Llama 3.2 1BMeta102.0
  4. #248INTELLECT-1Prime Intellect100.9
  5. #249MPT-30BDatabricks100.7
  6. #250LLaMA-13BMeta100.6
  7. #251Llama 2-7BMeta99.1

Sources