in the loop

Falcon 2 11B
#228 of 274 scored.

TIIMay 9, 2024Open weights

Capabilities Index

Range 99.8–115.6

109.6

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

No independent scores yet.

Epoch AI hasn't run Falcon 2 11B yet. Its scores show up here the morning after they do.

Everything else Epoch has for it

  • HellaSwag77.2%
  • Winogrande56.6%
  • GSM8K53.8%
  • MMLU44.5%

On the index

Around it.

  1. #225Gemma 7BGoogle112.0
  2. #226DeepSeek LLM 67BDeepSeek110.5
  3. #227LLaMA-65BMeta110.2
  4. #228Falcon 2 11BTII109.6
  5. #229Mistral 7B v0.3Mistral109.0
  6. #230DeepSeek-Coder-V2-Lite-BaseDeepSeek108.9
  7. #231PaLM 2-MGoogle108.3

Sources