Expired60% confidenceBenchmarkExact time
Sol scored 53.6 on Agent's Last Exam, which is 13.1 points higher than Claude Fable 5.
2
Sources
60%
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
VerifiedIn the Agents' Last Exam benchmark, GPT-5.6 Sol achieved a score of 53.6, which is 13.1 points higher than Claude Fable 5 using adaptive reasoning.77% similarUnverifiedSol's X-High tier achieved 53.6% on Agent's Last Exam at approximately $760, actually surpassing the Max tier.76% similarUnverified在长周期智能体工作流测试（Engines Last Exam）中，GPT-5.6 Sol 得分 53.6，比 Faber-5 高出 13.1 分71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501590API
curl https://kongchang.com/api/v1/knowledge/claims/501590MCP
get_claim(id=501590)