Unverified50% confidenceBenchmarkExact time
GPT-6 Sol exhibited lid clipping and component interpenetration issues in the 3D contact lens case task, with Opus ultimately scoring 10 points and Sol scoring 6 points.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/30/2026
First Seen
Valid until: 12/29/2026
Sources
Related Entities
Related Claims
UnverifiedGPT-5.6's clear weaknesses are concentrated in front-end visual tasks, with Sol scoring only six or seven points on projects such as Three.js and SVG, while Fable 5 can score nine or even full marks.72% similarUnverifiedGPT-6 Sol scored 98 points on the 3D-printed phone stand question (4x weight), 99 points on the operations assistant landing page question, and 96 points on the 3D shooter game question.72% similarUnverifiedGPT-6 Sol exhibits insufficient detail reproduction in modeling tasks, such as the claw machine losing Hello Kitty elements and the sofa cushions differing noticeably from the original image.72% similarUnverifiedThe initial game visuals generated by GPT-6 Sol were rough, but the results improved noticeably after switching to Extra mode.71% similarUnverifiedIn a 3D Rubik's Cube interaction test, the cube generated by GPT-5 became completely deformed as soon as it was manipulated, rendering it unusable.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/961362API
curl https://kongchang.com/api/v1/knowledge/claims/961362MCP
get_claim(id=961362)