ResearchTasksResume Quality JudgmentResume Quality JudgmentFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedResume screening dataset ground truth GPT-5.1Qwen3-8B (AutoScreen-FW)86.82Accuracy6Mar 20, 2026Resume Screening GPT-o3 labelsGPT-5-mini73.87Accuracy6Mar 20, 2026Resume quality judgment GPT-5.2 as ground truthGPT-5-mini69.17Accuracy6Mar 20, 2026