ResearchTasksResponse Length PredictionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedQwen 7B 2.5TPV6.38Avg VRAM (MB)7Feb 26, 2026Llama 3.2 3BEGTP5.52Avg VRAM (MB)7Feb 26, 2026Arena-Human-Preference-100k (test)RLP42.71MAE6Feb 26, 2026