Unverified50% confidenceBenchmarkExact time
In the Agent benchmark published by Meta, Muse Wonder overtook Claude Opus 5.5 on long-horizon coding and legal tasks.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
Related Entities
Related Claims
UnverifiedIn Meta's own Agent benchmark, Muse Wonder scored 10.0 on the Harvey LAB-AA legal task, and Claude Opus 5.5 scored 4.2.74% similarUnverifiedIn the API-available version of Muse Wonder, it beat Claude Opus 5.5 on the SWE-Marathon benchmark.73% similarUnverifiedClaude Opus 5.5 is the absolute flagship of Anthropic's product line, while Muse Wonder is positioned as the smaller of Meta's two models, with its larger version being Muse Wonder Full (available only via Muse Code).68% similarUnverifiedMuse Wonder is being directly benchmarked against Claude 5.5-level models and belongs to the same capability tier.60% similarUnverifiedOpus 5.5's default reasoning tier is set to medium, which is also the officially recommended tier, with complex tasks adjustable to high.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034661API
curl https://kongchang.com/api/v1/knowledge/claims/1034661MCP
get_claim(id=1034661)