Unverified50% confidenceBenchmarkExact time
在HealthBench Professional基准上Mythos 5得66.0%，GPT-5.6 Sol得60.5%（长度校正后约64%）
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026
Sources
GPT-5.6 Sol对决Fable 5：半价能否媲美旗舰？
bilibiliYoutube力工7/6/2026
Related Claims
Unverified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76% similarUnverified在Health Bench Professional上，Soul达到60.5分，比GPT-5.5高出8.7分73% similarUnverified在Artificial Analysis的Omniscience幻觉指标上，GPT-5.6 Sol Max高达89%，高于Claude Fable的55%和GLM 5.2的28%73% 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%72% similarUnverifiedOpus 4.7每次解题的中位输出token数为60,000，而GPT 5.5仅需16,00071% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/249744API
curl https://kongchang.com/api/v1/knowledge/claims/249744MCP
get_claim(id=249744)