Unverified50% confidenceBenchmarkExact time
On Terminal Bench, the two Muse models scored 57.1 and 52 respectively, roughly on par with the 52 to 59 range of Fable, Astra, and Opus.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/13/2026
First Seen
Valid until: 10/27/2026
Sources
Related Entities
Related Claims
UnverifiedOpus 5.5 scored 67 on Humanity's Last Exam, Astra scored 57, and Fable 5.1 scored 65.55% similarUnverifiedBased on benchmark extrapolation, Haiku 5.5 may land at the same level as Astra (approximately 53 points).55% similarUnverifiedOn the DeepSuite benchmark, Muse Wonder topped the list with 79 points, the smaller version scored 78.8, Fable scored 67, Astra scored 71, and Opus 5.5 scored 74.53% similarVerifiedOn Terminal Bench 4.0, Opus 5.5 scored 66.4%, Astra scored 57.9%, Fable 5.1 scored 55.8%, and the previous generation Opus 5 scored 52.3%.53% similarUnverifiedOpus 5.5 is not first across the board: on Automation Bench it scored 40, slightly below Astra's 41.4, and on Terminal Bench Science it trails GPT-6 Astra.53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013540API
curl https://kongchang.com/api/v1/knowledge/claims/1013540MCP
get_claim(id=1013540)