tables-in-markdown

Poe Bots

Official

Anthropic

Bot	Points	Introduction
Claude-3.5-Sonnet	324	Anthropic’s Claude 3.5 Sonnet using the October 22, 2024 model snapshot. Excels in complex tasks like coding, writing, analysis and visual processing. Has a context window of 200k of tokens (approximately 150k English words).
Claude-3.7-Sonnet	811	Anthropic’s most intelligent model. Claude 3.7 Sonnet is a hybrid reasoning model, producing near-instant responses or extended, step-by-step thinking. For the maximum extending thinking, please use https://poe.com/Claude-3.7-Sonnet-Reasoning. Supports a 200k token context window.
Claude-3.7-Sonnet-Reasoning	2371	Anthropic’s most intelligent model (with reasoning capabilities on by default). Claude 3.7 Sonnet is a hybrid reasoning model, producing near-instant responses or extended, step-by-step thinking. Recommended for complex math or coding problems. Supports a 200k token context window.

Google

Bot	Points	Introduction
Gemini-2.0.Pro	0	Gemini 2.0 Pro is Google’s latest most capable model with frontier performance on various key benchmarks; supports web search and tool use. Has low rate limits – please use https://poe.com/Gemini-2.0-Flash if you experience frequent errors. Supports 2 million tokens of input context. Temporarily free for subscribers only while in beta.
Gemini-2.0-Flash	7	Gemini 2.0 Flash is Google’s most popular model yet with enhanced performance and blazingly fast response times; supports web search grounding so can intelligently answer questions related to recent events. Notably, 2.0 Flash even outperforms 1.5 Pro on key benchmarks, at twice the speed. Supports 1 million tokens of input context.

OpenAI

Bot	Points	Introduction
o1	4549	OpenAI’s o1 is designed to reason before it responds and provides world-class capabilities on complex tasks (e.g. science, coding, and math). Improving upon o1-preview and with higher reasoning effort, it is also capable of reasoning through images and supports 200k tokens of input context. By default, uses reasoning_effort of “medium;” ability to customize reasoning effort per message coming soon.
o1-mini	452	Small version of OpenAI’s o1 model, which is designed to spend more time thinking before it responds but at a better performance profile. Can reason through complex tasks in science, coding, and math. For most tasks, https://poe.com/o3-mini will be better. Supports 128k tokens of context.
o1-pro	9070	OpenAI’s o1 pro highly capable reasoning model, tailored for complex, compute- or context-heavy tasks, dedicating additional thinking time to deliver more accurate, reliable answers. For less costly, complex tasks, https://poe.com/o3-mini is recommended.
o3-mini	266	o3-mini is OpenAI’s most recent reasoning model, providing high intelligence on a variety of tasks and domains, including science, math, and coding. This bot uses low reasoning effort by default but can low, medium & high can be selected; supports 200k tokens of input context and 100k tokens of output context.
o3-mini-high	552	o3-mini-high is OpenAI’s most recent reasoning model with reasoning_effort set to high, providing frontier intelligence on most tasks. Like other models in the o-series, it is designed to excel at science, math, and coding tasks. Supports 200k tokens of input context and 100k tokens of output context.
DALL-E-3	1500	OpenAI’s most powerful image generation model. Generates high quality images with intricate details based on the user’s most recent prompt. Use “–aspect” to select an aspect ratio (e.g –aspect 1:1). Valid aspect ratios are 1:1, 7:4, & 4:7.
GPT-4.5-Preview	6950	A research preview of GPT-4.5, a model designed to be more conversational, empathetic & helpful than past models in the GPT series, and with greater world knowledge. Recommended for use cases related to writing & communication, learning & tutoring, coaching & self-help, and brainstorming. You may experience errors and slower responses at times of peak usage. Supports a 128k token context window.

This site is open source. Improve this page.