ResearchTasksFaithful CalibrationFaithful CalibrationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAverage across datasets (PQA, SA, SQA, HE, MMLU, SQ, MT, UM, AC, SG)Qwen3-4B + RLMF + Rewr.0.85cMFG*27Jul 1, 2026PQAQwen3-1.7B + RLMF + Rewr.89cMFG*27Jul 1, 2026Faithful Calibration Dataset Suite (PQA, SA, SQA, HE, MMLU, SQ, MT, UM, AC, SG) (test)RLMF85PQA15Jul 1, 2026
Average across datasets (PQA, SA, SQA, HE, MMLU, SQ, MT, UM, AC, SG)Qwen3-4B + RLMF + Rewr.0.85cMFG*27Jul 1, 2026
Faithful Calibration Dataset Suite (PQA, SA, SQA, HE, MMLU, SQ, MT, UM, AC, SG) (test)RLMF85PQA15Jul 1, 2026