Unverified50% confidenceBenchmarkExact time
In the survival game Arena experiment, approximately 100 agents working in parallel completed the task in about 20 minutes, whereas sequential execution would have taken several hours.
1
Sources
50%
Confidence
Long-term
Relevance
10/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPilot experiments had three coding agents and eight models each run eight 20-minute single-pass tasks, with label-aware F1 showing extremely high variance ranging from 0.143 to 0.892.74% similarUnverifiedPowerful AI agents executing complex tasks often require about ten minutes rather than a few seconds.74% similarUnverifiedAgent tasks may involve multiple rounds of model calls, external tool execution, and human intervention, with the entire task lifecycle potentially lasting several minutes or longer.73% similarUnverifiedThe Onyx project had 120 automated research agents discover a physical model for a robotic actuator within 1.5 hours, completing research work that traditionally takes weeks.72% similarUnverified一个包含5个Agent、每Agent平均10轮推理、每轮2000 Token的任务单次执行约消耗10万Token，而等效确定性工作流可能只需一次几百Token的调用71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/981949API
curl https://kongchang.com/api/v1/knowledge/claims/981949MCP
get_claim(id=981949)