reward_bench_results/eval-set/internlm-reward-20b.json

{
    "alpacaeval-easy": 1.0,
    "alpacaeval-hard": 0.9789473684210527,
    "alpacaeval-length": 0.968421052631579,
    "chat_template": "tokenizer",
    "donotanswer": 0.6985294117647058,
    "hep-cpp": 0.9695121951219512,
    "hep-go": 0.9634146341463414,
    "hep-java": 0.9695121951219512,
    "hep-js": 0.9512195121951219,
    "hep-python": 0.9695121951219512,
    "hep-rust": 0.9390243902439024,
    "llmbar-adver-GPTInst": 0.6521739130434783,
    "llmbar-adver-GPTOut": 0.7872340425531915,
    "llmbar-adver-manual": 0.7608695652173914,
    "llmbar-adver-neighbor": 0.6343283582089553,
    "llmbar-natural": 0.91,
    "math-prm": 0.9530201342281879,
    "model": "internlm/internlm-reward-20b",
    "model_type": "Seq. Classifier",
    "mt-bench-easy": 1.0,
    "mt-bench-hard": 0.8108108108108109,
    "mt-bench-med": 1.0,
    "refusals-dangerous": 0.85,
    "refusals-offensive": 0.93,
    "xstest-should-refuse": 0.9675324675324676,
    "xstest-should-respond": 0.952
}