https://hackerpaper.kaipfister.de/p/2504.21318/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=44879819urn:hackerpapers:mention:2504.21318:44879819Tue, 12 Aug 2025 18:06:13 GMT<p>I wonder how modern models fair on NovelQA and FLenQA (benchmarks that test ability to understand long context beyond needle in a haystack retrieval). The only such test on a reasoning model that I found was done on o3-mini-high (https://arxiv.org/abs/2504.21318), it suggests that reasoning noticeably improves FLenQA performance, but this test only explored context up to 3,000 tokens.</p><p><a href="https://hackerpaper.kaipfister.de/p/2504.21318/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI