Expired50% confidenceBenchmarkExact time
In front-end and visual tasks, Sol scores only 6 to 7, while Fable 5 scores 9 or 10.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/10/2026
First Seen
Valid until: 10/8/2026(expired)
Sources
GPT-5.6 Three-Model Showdown: A Complete Breakdown of So, Terra, and Luna
bilibili宙流AI小工坊主7/9/2026
Related Claims
UnverifiedOn front-end and visual tasks, Soul can only score six to seven points, while Fable 5 can score nine to ten points.81% similarUnverifiedIn front-end and visual tasks (Three.js, SVG, etc.), Sol scores only 6 to 7, while Fable 5 consistently scores 9 to 10, indicating that front-end remains a weak area for OpenAI.70% similarUnverified跑分排名不等于所有场景的实际表现，Terra跑分接近5.5但游戏任务中5.5完成度略高62% similarUnverified在盲测中Sol给Opus方案打8.3分、给Fable方案打6.0分59% similarUnverifiedMiniMax M2.7 asks 0.6 questions per task, but its clarification advancement rate is only 60.7%, indicating a problem of low-information-gain questioning56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/471365API
curl https://kongchang.com/api/v1/knowledge/claims/471365MCP
get_claim(id=471365)