Expired50% confidenceBenchmarkExact time
The Sol configuration answered all of the first 6 out of 10 runs correctly in HIGH mode, and maintained a perfect score across multiple runs in XH mode.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/20/2026
First Seen
Valid until: 10/18/2026(expired)
Sources
Related Claims
UnverifiedIn full-fidelity prototype comparisons, Sol won three to four out of five times.67% similarUnverifiedSol 在编程智能体指数全推理模式下拿到 80 分，刷新 SOTA，比 Faber-5 高 2.8 分63% similarUnverifiedThe Luna configuration answered all 10 tests incorrectly in both HIGH and XH modes, with an accuracy rate of zero.62% similarUnverifiedWhen Sol uses medium inference intensity, it still leads competitors by 11.4 points, with an estimated cost of approximately one-quarter of that of competitors.62% similarUnverified在盲测中Sol给Opus方案打8.3分、给Fable方案打6.0分62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/573186API
curl https://kongchang.com/api/v1/knowledge/claims/573186MCP
get_claim(id=573186)