Expired50% confidenceBenchmarkExact time
In the ExploitBench test, Sol scored approximately 76%, slightly behind Fable 5's 78%, but Sol consumed only about 120,000–130,000 tokens while Fable 5 used approximately 350,000 tokens.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026(expired)
Sources
Fable 5对决GPT-5.6 Sol：基准测试、定价与AI权力博弈深度解析
bilibili黑纹白斑马7/3/2026
Related Claims
UnverifiedOn the Exploit Bench cybersecurity benchmark, Sol scores approximately 76% and Mythos 5 approximately 78%.69% similarUnverifiedSol scored 9019 points on the Terminal Bench 2.1 programming benchmark.66% similarUnverified在ELE测试中等推理强度下，Sol的成本约为Faber-5的1/4，Terra和Luna成本仅约1/16且得分仍超过Faber-565% similarUnverifiedOn the Exploit Bench cybersecurity vulnerability analysis test, SOL performs comparably to Anthropic's Codex, but produces only about one-third the output token count of the latter.63% similarUnverified普通版 Sol 在 Terminal Bench 2.1 基准测试中获得 88.8%，开启 Ultra 模式后提升至 91.9%63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/243180API
curl https://kongchang.com/api/v1/knowledge/claims/243180MCP
get_claim(id=243180)