Unverified50% confidenceBenchmarkExact time
Among the 14 benchmarks listed on Meta's model card, Muse Wonder (the API version) achieved 5 wins and 9 losses against Claude Opus 5.5.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedAmong the 14 benchmarks Meta itself published, Muse Wonder won 5, mainly in long-horizon coding, legal agent tasks, and Meta's internal memory tests; it lost 9, including ProgramBench (Opus leads 70.5 to 50.0).77% similarUnverifiedMeta's chart shows Muse Wonder beating Claude Opus 5.5 on long-horizon coding tasks: DeepSWE score 78.8 versus 74.2, SWE-Marathon score 53.1 versus 46.3.73% similarUnverifiedOn SWE-Marathon, Muse Wonder scored 53.1 and Claude Opus 5.5 scored 46.3, sourced from Abundant AI; however, a footnote states that the comparison used different agent harnesses and is not a controlled common comparison.72% similarUnverifiedOn the Harvey LAB-AA legal benchmark, Muse Wonder scored 10.0 and Claude Opus 5.5 scored 4.2, doubling Wonder's score, but the highest score in the whole row is only Wonder Full's 13.1.68% similarUnverifiedOpus 5.5 surpassed contemporaneous competing products on almost all benchmarks.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1011247API
curl https://kongchang.com/api/v1/knowledge/claims/1011247MCP
get_claim(id=1011247)