← Back to feed Tech & Digital

SWE-bench Verified no longer measures frontier coding capabilities

Hacker News Best / 26 April 2026 / 8h ago
SWE-bench Verified no longer measures frontier coding capabilities
Culture Index
63
Score Breakdown
Relevance
3/25
Freshness
25/25
Authority
18/20
Brand Signal
15/15
Depth
2/15
5-Axis Cultural Radar
Relevance Freshness Authority Brand Depth
Article URL: https://openai.com/index/why-we-no-longer-evaluate-swe-bench-verified/ Comments URL: https://news.ycombinator.com/item?id=47910388 Points: 211 # Comments: 124
Read Full Article → Hacker News Best ↗

More in Tech & Digital

TechCrunch

Apple under Ternus: what comes next for the tech giant’s hardware strategy

81
Techmeme

Epoch AI: Google controls ~25% of global AI compute, with ~3.8M TPUs and 1.3M GPUs; Google Cloud CEO Thomas Kurian says demand and revenue justify the spend (Stephen Morris/Financial Times)

78
Techmeme

Inside Andon Market, billed as the first retail boutique run by an AI agent; the Andon Labs experiment uses a Claude Sonnet 4.6-based agent to run the boutique (Heather Knight/New York Times)

77