Unverified50% confidenceBenchmarkExact time
Muse Wonder Full scored 30 on the AA-Omniscience factual recall test.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/17/2026
First Seen
Valid until: 10/31/2026
Sources
Related Entities
Related Claims
UnverifiedIn Artificial Analysis's independent evaluation, on the AA-Omniscience (knowledge) metric Opus 5.5 scored 46 and Muse Wonder scored 25.62% similarUnverifiedAt release, Muse Wonder was ranked 9th out of 219 models by Artificial Analysis.62% similarUnverifiedIn the most difficult single-concept quantitative category, most models' accuracy falls below 30%59% similarUnverifiedSetting Muse Wonder's reasoning effort to none returns HTTP 400, because the model always reasons.59% similarUnverifiedAIME has only 30 samples; claiming superiority by bolding a score of 80 against a baseline of 79 after running 4 seeds is statistically untenable.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1051038API
curl https://kongchang.com/api/v1/knowledge/claims/1051038MCP
get_claim(id=1051038)