ResearchTasksAutomated GradingAutomated GradingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedASSISTments held-out (test)Teacher prior + Response embedding0.062MSE9Feb 26, 2026Synthetic Bilingual DatasetQwen3-8B Fine-tuned0.936Human Spearman Rho7Jun 11, 2026DT 4 tasksGUIDE71Accuracy6Mar 4, 2026DC 4 tasksGUIDE0.8Accuracy6Mar 4, 2026DI 11 categoriesGUIDE92Accuracy6Mar 4, 2026Bounce programming assignmentHuman0.958Accuracy5Feb 26, 2026