List your company

Code Generation on HumanEval (Calibration and Uncertainty Metrics)

81AUROCVEROIC
65.469.4573.577.55Apr 30, 2026

Evaluation results

MethodLinks
VEROICsetting=CMIS, inference_path=LLaMA-3.1-8B -> LLaMA-3.1-70B2026.0481480.160.4735.7
RISK PREDICTORsetting=CMIS, inference_path=LLaMA-3.1-8B -> LLaMA-3.1-70B2026.0480460.1660.4826.5
CONFIDENCE-THRESHOLDsetting=CMIS, inference_path=LLaMA-3.1-8B -> LLaMA-3.1-70B2026.0478420.1750.5057.4
OUTPUT-TRIGGERsetting=CMIS, inference_path=LLaMA-3.1-8B -> LLaMA-3.1-70B2026.0477410.1710.4957.2
PERIODICsetting=CMIS, inference_path=LLaMA-3.1-8B -> LLaMA-3.1-70B2026.0474380.1820.5227.6
RANDOMsetting=CMIS, inference_path=LLaMA-3.1-8B -> LLaMA-3.1-70B2026.0472330.1970.5298.4
FIXEDsetting=CMIS, inference_path=LLaMA-3.1-8B -> LLaMA-3.1-70B2026.0466260.2050.5849.6