Unverified50% confidenceBenchmarkExact time
On the CursorBench benchmark, Muse Wonder scored 46.1% at default effort.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/23/2026
First Seen
Valid until: 1/21/2027
Sources
Related Entities
Related Claims
UnverifiedThe run in which Artificial Analysis rated Muse Wonder 52 points used max reasoning effort, with about 54,000 output tokens per task.72% similarUnverifiedMuse Wonder Full's 57.5 score on SWE-Marathon used the xhigh reasoning setting.67% similarUnverifiedOn the AA Omniscience factual knowledge test, MuseWonderFull scored 30, the regular Muse Wonder 25, Claude Opus 5.5 46, GPT-6 Astra 43, and Gemini 4 Argon 42.67% similarUnverifiedMuse Wonder Full scored 56 on the Artificial Analysis v4.3 leaderboard, second globally, behind Claude Opus 5.5's 58; the standard version of Muse Wonder scored 52.66% similarUnverifiedMuse-Glimmer-30B在测试中通过了88%的题目66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1089159API
curl https://kongchang.com/api/v1/knowledge/claims/1089159MCP
get_claim(id=1089159)