Expired50% confidenceBenchmarkExact time
When 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/13/2026
First Seen
Valid until: 10/11/2026(expired)
Sources
GPT-5.6三档模型解析：Sol/Terra/Luna重写Agent成本结构
bilibiliTerminator-AI7/10/2026
Related Claims
UnverifiedIn full-fidelity prototype comparisons, Sol won three to four out of five times.68% similarUnverifiedSol scored 53.6 on Agent's Last Exam, which is 13.1 points higher than Claude Fable 5.63% similarUnverifiedThe 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.62% similarUnverifiedIn the agent ultimate exam covering long-horizon workflows across 55 professional domains, Sol scored 53.6, surpassing the benchmarked Fable 5 by 13.1 points.60% 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-559% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501591API
curl https://kongchang.com/api/v1/knowledge/claims/501591MCP
get_claim(id=501591)