search

OpenBMB / InfiniteBench

Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718
MIT License
244 stars 19 forks source link

fix code_debug task score computing #22

Closed Wangmerlyn closed 3 weeks ago

Wangmerlyn commented 3 weeks ago

Add more answer matching template for models like llama3.1 image