Verified70% confidenceBenchmarkExact time

On the SWE Bench Pro programming benchmark, Sonnet 5 achieved 63.2% and Opus 4.8 achieved 69.2%.

4

Sources

70%

Confidence

Medium-term (~90 days)

Relevance

7/19/2026

First Seen

Valid until: 10/17/2026

Sources

The Truth Behind Anthropic's Account Bans: Client Detection Logic and a Wave of AI Model Launches

Related Claims

VerifiedSonnet 5 achieved a score of 80.4% on Terminal Bench 2.1, approaching Opus 4.8.85% similar UnverifiedOn the SWE-Bench Pro benchmark, Sonnet 5 significantly trails Opus 4.8.80% similar UnverifiedThe previous-generation Sonnet 4.5 scored 61.4% on the OSWorld Verified benchmark.79% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/561860

API

curl https://kongchang.com/api/v1/knowledge/claims/561860

MCP

get_claim(id=561860)