DeepSWE Measuring frontier coding agents
DeepSWE is a new benchmark designed to evaluate frontier coding agents on complex software engineering tasks. It offers significant improvements over existing benchmarks by ensuring task originality, high diversity, and real-world complexity. The benchmark aims to provide a more accurate reflection of how advanced coding models perform in practical scenarios.
- ▪DeepSWE tasks are created from scratch, avoiding contamination from pretraining data.
- ▪The benchmark includes tasks from 91 repositories across five programming languages.
- ▪Solutions to DeepSWE tasks require significantly more code and output tokens compared to previous benchmarks.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | DeepSWE |
| Canonical URL | https://deepswe.datacurve.ai/ |
| Publication time | Wed, 27 May 2026 19:57:16 +0000 |
| Retrieval time | 2026-05-27T20:08:04.392Z |
| Last seen | 2026-05-27T20:08:04.392Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | zfbUQEpufOC1 |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
@keyframes deepswe-waves-draw { from { stroke-dashoffset: 1; } to { stroke-dashoffset: 0; } } .deepswe-waves-path { stroke: currentColor; stroke-opacity: 0.32; stroke-width: 3; stroke-dasharray: 1; stroke-dashoffset: 1; animation-name: deepswe-waves-draw; animation-fill-mode: forwards; animation-timing-function: cubic-bezier(0.25, 0.1, 0.25, 1); } @media (prefers-reduced-motion: reduce) { .deepswe-waves-path { animation: none; stroke-dashoffset: 0; } } DeepSWEbyMeasuring frontier coding agents on original, long-horizon engineering tasksRead the blogRun DeepSWEToday's leading public coding benchmarks are starting to saturate at the frontier: top models cluster within a narrow score band where adjacent configurations often overlap on confidence intervals.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DeepSWE.
Discussion
0 commentsMore from DeepSWE
