{"type":"analysis","id":"analysis:research-flint-s-89-7-is-on-scale-s-real-swe-bench-pro-v2-but-likely-sits-at-the-bottom","slug":"research-flint-s-89-7-is-on-scale-s-real-swe-bench-pro-v2-but-likely-sits-at-the-bottom","title":"Flint's 89.7% is on Scale's real SWE-bench Pro v2, but likely sits at the bottom of that board","description":"The review was wrong that the benchmark is undefined: Scale published it on September 22. It was right that Recursive never said which split, protocol or checkpoint produced the score, and nobody outside has rerun it.","published_at":"2026-11-09T23:00:00.000Z","updated_at":"2026-11-09T23:00:00.000Z","record_date":"2026-11-09","topics":["trends","research"],"source_urls":["https://arxiv.org/html/2610.24206","https://labs.scale.com/blog/swe-bench-pro-v2","https://huggingface.co/RecursiveSI/flint","https://recursive.com/updates/introducing-recursive-flint","https://labs.scale.com/leaderboard/swe_bench_pro_public_v2","https://www.machine.net/news/recursive-flint-open-coding-model-self-reported-benchmarks/","https://s5labs.io/resources/insights/recursive-flint-local-coding-model-apache"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-flint-s-89-7-is-on-scale-s-real-swe-bench-pro-v2-but-likely-sits-at-the-bottom/","markdown":"https://newruntime.com/analysis/research-flint-s-89-7-is-on-scale-s-real-swe-bench-pro-v2-but-likely-sits-at-the-bottom.md","json":"https://newruntime.com/analysis/research-flint-s-89-7-is-on-scale-s-real-swe-bench-pro-v2-but-likely-sits-at-the-bottom.json"},"author":{"role":"author","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"editorial_provenance":{"desk":"authorial","target_ref":"deep_research:d57952be-fe07-442d-a794-9e508d14ac60","authorial_article_id":"d57952be-fe07-442d-a794-9e508d14ac60"},"next_reads":[{"type":"collection","path":"/analysis/","url":"https://newruntime.com/analysis/","title":"Analysis","reason":"Open the latest authorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/analysis.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}