Unverified50% confidenceOpinionExact time
The tester ultimately concluded that Fable 5.1 remains their favorite model for most work.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedIn Cognition's Frontier Code evaluation, Fable 5 ranked first among all frontier models even with only medium reasoning intensity enabled.67% similarUnverifiedThe model's intelligence is essentially unimpaired on five real Coding Agent problems, with both the Preview and 0731 versions passing all tests.63% similarUnverifiedThe test concluded that the aesthetic version is the optimal base model, producing results more in line with anime aesthetics than the base version without requiring complex prompts59% similarUnverified在未被明确要求的情况下，Opus 5在处理公告模块时主动引入了富文本编辑器组件并完成自我测试58% similarUnverifiedReal-world feedback indicates that GLM-5.2's performance in CatPaw is basically consistent with the official version, and the model's capabilities are genuinely usable.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/897225API
curl https://kongchang.com/api/v1/knowledge/claims/897225MCP
get_claim(id=897225)