LLMs Overview

Online LLMs in PapersGPT

Today, AI is advancing at a very fast pace, with new models and techniques coming out almost every week. The race shows no signs of slowing down, with the leaderboard of top AI models shifting almost weekly. This guide will help you to get an overview of the LLMs. You can use most of the LLMs in PapersGPT to chat pdf. Below is the models supported in PapersGPT:

ProviderSupported Models
OpenAIgpt-5 | gpt-5-min | gpt-5-nano | gpt-5-chat
gpt-4.1 | gpt-4.1-mini | gpt-4.1-nano
o3 | o4-mini | o3-mini | o1-mini
gpt-4o | chatgpt-4o-latest | gpt-4o-mini | gpt-4 | gpt-4-turbo | gpt-3.5-turbo
Gemini2.5 Pro | 2.5 Flash | 2.5 Flash-Lite
2.0 Flash | 2.0 Flash-Lite
ClaudeOpus 4.1 | Opus 4 | Sonnet 4
Sonnet 3.7 | Sonnet 3.5 | Haiku 3.5
Opus 3 | Sonnet 3 | Haiku 3
DeepSeekDeepSeek 3.1
QwenQwen-Max | Qwen-Plus | Qwen-Flash
qwen3-235b-a22b-thinking-2507 | qwen3-235b-a22b-instruct-2507
qwen3-30b-a3b-thinking-2507 | qwen3-30b-a3b-instruct-2507
MistralMedium 3 | Small 3.2 | Large
Kimikimi-k2-0711-preview | kimi-k2-turbo-preview
Z.aiglm-4.5 | glm-4.5-air | glm-4.5-flash
OpenRouterClaude Sonnet 4 | Gemini 2.0 Flash | Gemini 2.5 Flash | DeepSeek V3 03244 | Qwen3 Coder | Gemini 2.5 Pro | Claude 3.7 Sonnet | DeepSeek R1 0528 | Kimi K2 | gpt-oss-120b | GLM 4.5 | GPT-5 | Mistral Nemo | Qwen3 30B A3B | Gemini 2.5 Flash Lite | GLM 4.5 Air | GPT-4o-mini | Claude Opus 4.1 | gpt-oss-20b | Mistral Medium 3.1 | Grok 4 | Llama 3.3 70B Instruct | Grok 3 Mini | Grok 3
SiliconFlowgpt-oss-120b | gpt-oss-20b | DeepSeek-V3 | DeepSeek-R1 | GLM-4.5 | GLM-4.5-Air | Qwen3-235B-A22B-Thinking-2507 | Qwen3-235B-A22B-Instruct-2507 | Qwen3-30B-A3B-Thinking-2507 | Qwen3-30B-A3B-Instruct-2507 | Kimi-K2-Instruct | ERNIE-4.5-300B-A47B | Hunyuan-A13B-Instruct | MiniMax-M1-80k

Please note that OpenRouter and SiliconFlow are models hubs which supply the most popular SOTA models.

How to judge and choose a model?

With so many models available on the market, how do you choose the right one? Here are two reference platforms to consider:

* OpenRouter, which contains numerous models and is used by a large number of users. Therefore, the top 20 most-used models listed above are worth considering. However, it's best to prioritize them based on their intended use, as some models are better suited for coding but not necessarily for reading comprehension.

* lmarena.ai, a LLM benchmark platform, which judges models all by the manual comparative evaluation, and the evaluation is also a black box scoring system set up according to different usage scenarios.

In addition, if you use LLM frequently, a cost-effective economic model is also a point worth considering when choosing. For details, please see this article.