Unverified50% confidenceBenchmarkExact time
All three models (Sol, Luna, and DeepSeek) failed to accurately reproduce multi-image layouts, which was a common shortcoming.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/29/2026
First Seen
Valid until: 12/28/2026
Sources
Related Entities
Related Claims
UnverifiedThe three names Sol, Terra, and Luna represent capability tiers rather than generation numbers, with Sol being the flagship and most powerful, Terra targeting high-frequency daily work, and Luna focusing on cost-effectiveness.64% similarUnverified综合实测结果，四款模型能力排名为：Sol > GPT-5.5 > Terra > Luna56% similarUnverifiedThe thinking intensity levels set for the test were: Max for Sol and DeepSeek, and High for Luna.56% similarUnverifiedThe four models participating in the test are QDAM 3.7 Plus, LongCat 2.0, DeepSeek Feast Pro, and MiniMax Mi3.56% similarUnverifiedIn the new version of the 24-point problem (numbers 2, 7, 8, 10, requiring three different solutions), DeepSeek V4.1 Flash got all three solutions wrong, each violating the constraint that each number can only be used once.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/958960API
curl https://kongchang.com/api/v1/knowledge/claims/958960MCP
get_claim(id=958960)