evalscope: Optimize LLMs
From the repo · “A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.”
Evaluates large language models efficiently to check their performance.
"A founder building a product with a large language model wants to compare its performance with another model. They use evalscope to create a custom evaluation framework and run it on both models, getting results in under an hour."
- •When you need to compare the performance of different large models on your dataset
- •When you want to optimize your model's performance on a specific task or metric
- •When you need to evaluate the effectiveness of your model in a production environment
Run an evaluation task using `evalscope run --config-path=configs/llm_benchmark.yml --model-name=mymodel --dataset=mydataset`
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Installs with a command or two; your AI agent can do it for you.
mkdir -p ~/.claude/skills/evalscope && curl -fsSL https://workflowstacks.com/api/skills/evalscope/claude-skill -o ~/.claude/skills/evalscope/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Evalscope: Optimize LLMs is a very large Python project (~209k lines across 1320 code files, plus 257 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.
- 1README.mdStart here — what it does and how to install it
- 2AGENTS.mdThe instructions the AI actually follows
- 3evalscope/run.pyWhere the program starts running
- 4pyproject.tomlDependencies and the commands it exposes
- 5evalscope/__init__.pyInside evalscope/ — the main logic begins here
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Installs with a command or two; your AI agent can do it for you.
mkdir -p ~/.claude/skills/evalscope && curl -fsSL https://workflowstacks.com/api/skills/evalscope/claude-skill -o ~/.claude/skills/evalscope/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Are you the creator of this tool? and earn 85% of every sale.
Show it off in your README:
[](https://workflowstacks.com/skills/evalscope?utm_source=github&utm_medium=badge)The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.
Related skills
More ai-agent tools founders pair with this one.