{"data":{"slug":"swe-bench","etype":"benchmark","name":"SWE-bench Verified","cat":"Capability","subtitle":"Real GitHub issues, real repos — the coding-agent standard.","summary":"SWE-bench gives a model an actual repository and issue; success means a patch that passes the tests. The Verified subset (human-validated, with OpenAI) became the metric coding agents live by — from single digits in 2023 to ~80% at the 2025 frontier — and the number behind every 'AI software engineer' claim.","attrs":null,"kf":null,"aliases":["SWEbench","SWE bench"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":null,"region":null,"asof":"2026-01-15","sources":[{"url":"https://www.swebench.com/","label":"SWE-bench"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T05:45:14+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}