in the loop

PaLM 2-L
#217 of 274 scored.

GoogleMay 17, 2023

Capabilities Index

Range 106.2–128.1

115.0

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

No independent scores yet.

Epoch AI hasn't run PaLM 2-L yet. Its scores show up here the morning after they do.

Everything else Epoch has for it

  • TriviaQA86.1%
  • HellaSwag82.4%
  • Winogrande66.0%
  • ARC AI258.9%

On the index

Around it.

  1. #214Qwen2.5-Coder-14BAlibaba116.4
  2. #215Gemma 3 4BGoogle · $0.05 in116.0
  3. #216GPT-3.5 Turbo (Jan 2024)OpenAI115.7
  4. #217PaLM 2-LGoogle115.0
  5. #218Llama 2-70BMeta113.8
  6. #219GPT-3.5 Turbo (Jun 2023)OpenAI113.4
  7. #220Qwen2.5-Coder (7B)Alibaba113.1

Sources