OpenAI reports AutomationBench results for GPT-6 Sol vs. task cost
X ● Covered by 7 sources
OpenAI reports that its GPT-6 Sol scored 33.2% on AutomationBench at $0.27 per task. The comparison cites Luna achieving similar factuality at about one-hundredth the cost. OpenAI frames the result as a shift toward lower-cost task completion while maintaining comparable factuality.
Why it matters
OpenAI highlights Sol scoring 33.2% on AutomationBench at $0.27 per task. The newsletter contrasts this with Luna’s higher-effort approach, claiming similar factuality at about one-hundredth the cost.