Unverified50% confidenceBenchmarkExact time
在Exploit Bench网络安全基准上，Sol得分约76%，Mythos 5约78%
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026
Sources
Fable 5对决GPT-5.6 Sol：性价比重塑前沿AI格局
bilibili英文白斑马7/3/2026
Related Claims
Unverified在Terminal Bench 2.1上Sol Ultra模式接近92%，超过Mythos 5的88%73% similarUnverified在病毒学多选基准上，Mythos 5得分56%，GPT-5.6 Sol得分55.5%，几乎持平且均远超专家基线69% similarUnverifiedExploitBench测试中Sol约76%略逊于Fable 5的78%，但Sol仅消耗约12-13万Token而Fable 5用约35万Token69% similarUnverified在SWE-Bench Pro编程评测上，Claude Fable 5以80%的成绩领先GPT-5.6 Sol的64.6%69% similarUnverified在贴吧小站项目评测中，Sol以83.95分居首，GLM 5.2以76.59分位列第二，Terra 75.97分排第三，Luna 68.56分排第四66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/248320API
curl https://kongchang.com/api/v1/knowledge/claims/248320MCP
get_claim(id=248320)