Unverified50% confidenceOpinionExact time
Wonderhop's data is only statistically meaningful when the player base is large enough.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAccording to Artificial Analysis evaluation, WonderFull scores 56 on the intelligence index, a significant improvement over the previous 48; its coding Agent score is 68.63% similarUnverifiedAccording to Artificial Analysis's test data, the Muse Wonder model consumes about 54,000 output tokens per task on average at max effort.57% similarUnverified1700万坐标点仅对应350场游戏，对深度学习任务而言只属于概念验证级别数据集57% similarUnverifiedIn the 14-benchmark comparison on Meta's own scorecard, Muse Wonder won 5 and lost 9, while Wonder Full won 8 and lost 6.56% similarUnverifiedArtificial Analysis gives Muse Wonder an intelligence index of 52, ranking 9th out of 219 models; Claude Opus 5.5 is 58, Astra is 53, and Wonder Full is 56.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1047635API
curl https://kongchang.com/api/v1/knowledge/claims/1047635MCP
get_claim(id=1047635)