List your company

Interactive Deep Research on Interactive Deep Research (evaluation set)

85.7AlignSTEER
61.821668.020874.2280.4192May 22, 2026

Evaluation results

MethodLinks
STEERBase pause cost (C0)=0.72026.0585.786.4579.9788.6791.2983.0484.19
GPT-ResearcherPersona Setting=full-persona2026.0579.4883.8377.9387.0990.3179.0582.58
OpenDeepResearchPersona Setting=full-persona2026.0577.286.174.0283.4287.6273.1879.44
o4-mini-deep-researchPersona Setting=full-persona2026.0575.7286.0275.5487.1987.3685.0182.63
GPT-ResearcherPersona Setting=initial-persona2026.0574.5981.6879.0587.3788.7175.5281.71
o4-mini-deep-researchPersona Setting=initial-persona2026.0572.7386.0975.7689.189.5186.7482.76
OpenDeepResearchPersona Setting=initial-persona2026.0569.7985.4572.5181.6484.1268.9877.44
GPT-Researcher2026.0566.6378.4281.886.388.476.681.25
OpenDeepResearch2026.0562.7483.7274.982.488.8568.3981.25