Open-World Evaluations for Measuring Frontier AI Capabilities
The paper discusses the importance of open-world evaluations in measuring AI capabilities. It highlights the limitations of traditional benchmark-based evaluations and proposes a new approach for assessing AI through real-world tasks. The authors introduce a project called CRUX aimed at conducting these evaluations regularly.
- ▪Benchmark-based evaluations can overstate or understate AI capabilities.
- ▪Open-world evaluations involve long-horizon, messy tasks assessed qualitatively.
- ▪The authors conducted an evaluation where an AI agent developed an iOS application with minimal human intervention.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 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 | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.20520 |
| Publication time | Fri, 22 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-22T04:02:00.009Z |
| Last seen | 2026-05-22T04:02:00.009Z |
| 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 | kw3V62PY_OpT |
| 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
Computer Science > Artificial Intelligence arXiv:2605.20520 (cs) [Submitted on 19 May 2026] Title:Open-World Evaluations for Measuring Frontier AI Capabilities Authors:Sayash Kapoor, Peter Kirgis, Andrew Schwartz, Stephan Rabanser, J.J. Allaire, Rishi Bommasani, Harry Coppock, Magda Dubois, Gillian K Hadfield, Andrew B. Hall, Sara Hooker, Seth Lazar, Steve Newman, Dimitris Papailiopoulos, Shoshannah Tekofsky, Helen Toner, Cozmin Ududec, Arvind Narayanan View a PDF of the paper titled Open-World Evaluations for Measuring Frontier AI Capabilities, by Sayash Kapoor and 17 other authors View PDF HTML (experimental) Abstract:Benchmark-based evaluation remains important for tracking frontier AI progress.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
