GRM-2.5 / .eval_results /mmlu_pro.yaml
DedeProGames's picture
Create mmlu_pro.yaml
9b11179 verified
raw
history blame contribute delete
193 Bytes
- dataset:
id: TIGER-Lab/MMLU-Pro
task_id: mmlu_pro
value: 80.1
source:
url: https://huggingface.co/OrionLLM/GRM-2.5/
name: Official GRM-2.5 Benchmark
user: DedeProGames