Unverified50% confidenceBenchmarkExact time
Terminal-Bench 4.0 has a standard error of ±2.6 points, and Opus 5's 51.8% reproduced as 52.3%, which Anthropic calls noise.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
VerifiedOn 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%.70% similarUnverifiedThe Claude model's score on the Terminal Bench 4.0 terminal coding benchmark improved from 42% to nearly 56%.68% similarUnverifiedFable 5.1 scored 52.6% on the Terminal Bench Science 0.1 benchmark, more than doubling the score of its previous generation.64% similarUnverifiedAcross a range of question sizes spanning 256x, the error judgment rate of a single run is almost unchanged: 0.531 at T=16 and 0.534 at T=4096.64% similarUnverifiedHaiku 5.5's score on Terminal Bench 4.0 rose from 0% in the previous generation to 39.2%.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1025659API
curl https://kongchang.com/api/v1/knowledge/claims/1025659MCP
get_claim(id=1025659)