Unverified50% confidenceBenchmarkExact time
SWE-2在FrontierCode 1.1 Main基准测试上取得了50.0%的成绩
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/13/2026
First Seen
Valid until: 12/12/2026
Sources
Related Entities
Related Claims
UnverifiedSWE-2在Terminal-Bench 2.1基准测试中取得了92.8分的成绩66% similarUnverifiedSWE-2的基准得分与竞品Fable 5.1相差不到一个百分点,但成本低了64%65% similarUnverified根据SWE-Bench Verified基准测试,Qwen 2.5 Coder 32B的编码能力评分达到61.7分60% similarUnverified微调后的 YOLOv8s 在 shahed 类别上达到了 mAP@50 99.5% 的成绩60% similarUnverified在AID基准测试中,o1 high(对应o1 pro)的编程能力得分超过60,优于o3-mini-high,但两者非常接近60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/918908API
curl https://kongchang.com/api/v1/knowledge/claims/918908MCP
get_claim(id=918908)