Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Deep Search and Research Reasoning on xbench DeepSearch 2510 (Pass@1)

75Pass@1 Accuracy

Tongyi DeepResearch

4955.7562.569.25Oct 28, 2025
Updated 15d ago

Evaluation Results

MethodLinks
2025.10
75
2025.10
71
2025.10
70
2025.10
69
2025.10
67
2025.10
65
2025.10
50