ResearchTasksFile Understanding and GenerationFile Understanding and GenerationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedFileSysDoubao-2.0-Pro77.5Score12Jun 16, 2026GTAClaude-4.6-Sonnet-Thinking77.9Score12Jun 16, 2026GAIA FileClaude-4.6-Sonnet-Thinking79Score12Jun 16, 2026