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

Deep Research on DeepResearch Bench 1.0 (test)

46.45Overall Score

OpenAI-DeepResearch

33.304436.717240.1343.5428Jan 9, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
46.4546.4643.7349.3947.22
2026.01
44.6444.9641.9747.1445.59
2026.01
41.9939.7535.8748.5146.63
2026.01
40.4639.4634.4446.2244.27
2026.01
39.336.131.6647.6544.92
2026.01
38.2236.0830.8946.5942.17
2026.01
37.5133.8830.0145.7243.82
2026.01
37.5134.2728.8546.7743.21
2026.01
36.5933.228.345.5842.67
2026.01
36.1232.3127.7345.7242.33
2026.01
34.7931.2926.7943.8141.58
2026.01
33.8129.5724.2344.0541.02