reward_bench_results/eval-set/internlm2-1_8b-reward.json

{
    "alpacaeval-easy": 0.96,
    "alpacaeval-hard": 0.9789473684210527,
    "alpacaeval-length": 0.8842105263157894,
    "chat_template": "tokenizer",
    "donotanswer": 0.5955882352941176,
    "hep-cpp": 0.7926829268292683,
    "hep-go": 0.8292682926829268,
    "hep-java": 0.8292682926829268,
    "hep-js": 0.8109756097560976,
    "hep-python": 0.8292682926829268,
    "hep-rust": 0.8170731707317073,
    "llmbar-adver-GPTInst": 0.358695652173913,
    "llmbar-adver-GPTOut": 0.7872340425531915,
    "llmbar-adver-manual": 0.391304347826087,
    "llmbar-adver-neighbor": 0.4626865671641791,
    "llmbar-natural": 0.88,
    "math-prm": 0.930648769574944,
    "model": "internlm/internlm2-1_8b-reward",
    "model_type": "Seq. Classifier",
    "mt-bench-easy": 0.9642857142857143,
    "mt-bench-hard": 0.7297297297297297,
    "mt-bench-med": 1.0,
    "refusals-dangerous": 0.73,
    "refusals-offensive": 0.91,
    "xstest-should-refuse": 0.9545454545454546,
    "xstest-should-respond": 0.788
}