Unverified50% confidenceOpinionExact time
In the game generation test, the mini-game control system generated by Gemini 4 was "pretty bad", making the gameplay hard to understand, and characters got stuck; by contrast, the game generated by GPT 6.1 Sol was at least playable and characters did not run around everywhere.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/29/2026
First Seen
Valid until: 1/27/2027
Sources
Related Entities
Related Claims
UnverifiedIn the "Tower of Babel" 3D generation test, Gemini 4 showed floating figures, characters stuck motionless, rigid arrangement and problems with water handling, while the figures in GPT 6.1 Sol had clearer design intent and behavioral intent, with overall completion a level higher.75% similarUnverifiedIn a comparative test of strategy game development, Claude Opus 5.5 worked continuously for over 20 minutes and produced an in-depth game containing mechanics such as building animations and tactical logic, whereas Gemini 4 Argon gave a result after thinking for less than a minute, a notable gap.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1111597API
curl https://kongchang.com/api/v1/knowledge/claims/1111597MCP
get_claim(id=1111597)