【Evaluation】Best practice for evaluating Qwen3 with EvalScope !!

[wangxingjun778]

【Evaluation】Best practice for evaluating Qwen3 !!

For more details, please refer to: https://evalscope.readthedocs.io/en/latest/best_practice/qwen3.html
Power by: EvalScope https://github.com/modelscope/evalscope

1. Speed Benchmark
   
   

2. Benchmark collection (for evaluating abilities such as code、understanding、instruction following、math ...)
   NOTE: The result is based on samples of original benchmarks with eval arg --limit
   

3. Thinking efficiency of Qwen3
   
   

4. Run Gradio visualization

evalscope app

Get started and have fun ! :)