PaLM 2
Google's previous generation large language model
PaLM 2
Google • May 2023
Training Data
Up to early 2023
PaLM 2
May 2023
Parameters
~340 billion
Training Method
Transformer
Context Window
8,192 tokens
Knowledge Cutoff
April 2023
Key Features
Multilingual • Code Generation • Math & Science
Capabilities
Reasoning: Good
Coding: Good
Languages: Very Good
What's New in This Version
Improved multilingual and coding capabilities
Google's previous generation large language model
What's New in This Version
Improved multilingual and coding capabilities
Technical Specifications
Key Features
Capabilities
Other Google Models
Explore more models from Google
Gemini 3.5 Flash
Google's frontier Flash model built for agentic workflows, coding, and long-horizon tasks at high speed
Gemini 3.1 Flash-Lite
Google's most cost-efficient Gemini 3 model with 1M context, multimodal input, and 2.5x faster time-to-first-token than Gemini 2.5 Flash
Gemini 3.1 Pro
Google's newest flagship with doubled reasoning performance and 1M token context for agentic workflows
