askimo
★ 534
vs
chinese-llm-benchmark
★ 6.5k
askimo vs chinese-llm-benchmark
askimo: Askimo is a native desktop app that puts OpenAI, Claude, Gemini, Grok and local Ollama models in one chat client. It adds local RAG over your files, MCP tools, a script runner and the ability to delegate goals to agent CLIs such as Claude Code and Codex.; chinese-llm-benchmark: ReLE Benchmark (formerly CLiB) provides a continuously updated evaluation for Chinese AI large language models, covering over 337 commercial and open-source LLMs. It offers multi-dimensional capability assessments across various domains, along with comprehensive rankings and a large defect library for model improvement.
01
TL;DR
askimoLLM Infra · ★ 534
When to choose:
- You want one native desktop client for cloud models and local Ollama or LM Studio models.
- You want to chat with local folders and files through RAG without uploading them.
- You want to send work to Claude Code, Codex or Antigravity from the same app.
When to skip:
- You need permissive licensing for embedding in a hosted product: the licence is AGPLv3.
- You only want a lightweight chat window; this app bundles RAG, Plans, scripts, MCP and voice.
- You want a headless server or a library rather than a desktop app.
chinese-llm-benchmarkLLM Infra · ★ 6.5k
Comparing and selecting the best performing LLMs for specific applications.
02
Side-by-Side Comparison
Field
askimochinese-llm-benchmarkCategory
LLM Infra
LLM Infra
Stars
★ 534
★ 6.5k
License
AGPL-3.0
—
Install Command
—
git clone https://github.com/jeinlee1991/chinese-llm-benchmark.git
Updated
1d ago
2d ago
Open Source
Yes
Yes
Tags
ai, chat-client, rag
LLM Evaluation, Chinese LLMs, AI Benchmark
03
Features
askimo01Multi-provider chat: OpenAI, Claude, Gemini, Grok, Ollama, LM Studio, OpenRouter, vLLM and any OpenAI-compatible endpoint
02Local RAG over folders, files and web URLs with hybrid BM25 and vector retrieval
03MCP tool integration over stdio or HTTP
04Delegate goals to Claude Code, Codex or Antigravity, with reusable skills shared across agents
05Multi-step Plans, a Python/Bash/JavaScript script runner and local speech-to-text and text-to-speech
chinese-llm-benchmark01Extensive coverage of 337+ commercial and open-source Chinese LLMs.
02Multi-dimensional evaluation across 7 main domains and ~300 sub-dimensions.
03Provides detailed ranking lists for various capabilities and specific domains.
04Offers a large defect library with over 2 million LLM flaws for research and improvement.
05Supports customized model selection and free evaluation services for private models.
04
Use Cases
askimo↳Use one desktop client for several cloud and local models instead of juggling browser tabs
↳Search and chat with private local documents without uploading them
↳Hand a coding task to an agent CLI and watch its streamed tool calls
chinese-llm-benchmark↳Comparing and selecting the best performing LLMs for specific applications.
↳Identifying weaknesses and improving the capabilities of large language models.
↳Benchmarking private or custom LLMs against public models for performance and cost optimization.
05
Best For
askimoHidden Gem
chinese-llm-benchmarkEssentialTrending
FAQ
FAQ
What is the difference between askimo and chinese-llm-benchmark?
Both askimo and chinese-llm-benchmark are in the LLM Infra category. askimo has 534 stars, while chinese-llm-benchmark has 6.5k stars.
Which is better, askimo or chinese-llm-benchmark?
The best choice depends on your use case. Choose askimo if Use one desktop client for several cloud and local models instead of juggling browser tabs, and chinese-llm-benchmark if Comparing and selecting the best performing LLMs for specific applications..
Is askimo free or open source?
Yes, askimo is open source on GitHub (AGPL-3.0).
Is chinese-llm-benchmark free or open source?
Yes, chinese-llm-benchmark is open source on GitHub.
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→