Unverified50% confidenceBenchmarkExact time

Claude Opus 5.5 scores approximately 66.4 on Terminal Bench.

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

9/30/2026

First Seen

Valid until: 12/29/2026

Sources

Claude Opus 5.5, GPT-6 Sol/Luna Launch Same Night: AI Enters the Tiered Model Era

Related Entities

Claude Opus 5.5model Terminal Benchconcept

Related Claims

UnverifiedOn 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%.74% similar UnverifiedThe Claude model's score on the Terminal Bench 4.0 terminal coding benchmark improved from 42% to nearly 56%.72% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/962329

API

curl https://kongchang.com/api/v1/knowledge/claims/962329

MCP

get_claim(id=962329)