Unverified60% confidenceFactTime unknown
Claude achieved a task completion rate of 14.9% on the OSWorld benchmark, representing the highest level at the time.
2
Sources
60%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn this benchmark, LangGraph achieved a success rate of 77.6%, an average completion time of 31.2 seconds, and an average token cost of 12,143.65% similarUnverifiedDevin achieved a resolution rate of 13.86% on the SWE-bench evaluation (the highest at the time).65% similarUnverifiedIn the RULER-16K experiments, KVFetch improved the average score across 13 tasks by +8.4, with gains concentrated on tasks requiring sequential access.63% similarUnverifiedCompared to the strongest baseline, POrchestra improves average task success rate by 9.1%.63% similarUnverifiedBullet 在 SWE-bench Verified 基准测试中取得 95.8% 的成绩，位列前三，平均每个任务耗时 119 秒60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/29323API
curl https://kongchang.com/api/v1/knowledge/claims/29323MCP
get_claim(id=29323)