OEIS Open: general LLMs solve 147 of 492 Lean-formalised OEIS conjectures
Status
Not evaluated
Recorded on · arxiv.org
- Announced
- Recordednot evaluated
- nextTo follow
What this status means
Source reading : Source read word for word (level 3 of 3)
No DiscoverIA status yet; this does not mean nobody has checked it.
To move to “Under review”: a public review under way. To “Peer reviewed”: a journal publication or a review by named experts.
The gist
Adamczewski and co-authors (arXiv 2608.11941, 2026-08) report that general language models solve 147 of 492 OEIS conjectures formalised in Lean, about 30%. Status: not yet evaluated.
Cite this entry
A single status snapshot since Oct 11, 2026: a citation always points to a dated snapshot.
Cite snapshot 1, Oct 11, 2026
APA citation with the dated link
BibTeX @misc, key discoveria-oeis-open-benchmark-r1
@misc{discoveria-oeis-open-benchmark-r1,
author = {{DiscoverIA}},
title = {OEIS Open: general LLMs solve 147 of 492 Lean-formalised OEIS conjectures},
howpublished = {DiscoverIA registry, entry oeis-open-benchmark},
note = {Status « Not evaluated », snapshot 1, recorded on October 11, 2026. benchmark},
year = {2026},
url = {https://discoveria.ai/en/fiche/oeis-open-benchmark/#releve-1},
urldate = {2026-10-11}
}Dated link opens this snapshot in the history
Text written by an AI (DiscoverIA pipeline), on Reviewed by: nobody yetReport an error
What has not been reviewed?
The status and its sources come from the registry; only the explanatory text has not been reviewed. A reported error is corrected, then the text is reviewed.
The status and its sources come from the registry; only the explanatory text has not been reviewed. A reported error is corrected, then the text is reviewed.
Key facts
- Claimed by
- Adamczewski et al. (arXiv 2608.11941)
announced on Aug 2026 - Nature
- benchmark
- Field
- Mathematics (mathematics / benchmark)
- Checked by
- authors
- Sources (domains)
- 1 : 1 links only
- This entry
- AI draft, not reviewed
To understand
Analogy
It is like a common exam: several models sit the same series of tests and one counts how many each passes.
What it changes
An open benchmark provides a shared measure for comparing models on conjectures about number sequences, checked by Lean. If the figures held, about 30% of these conjectures would already be within reach of general-purpose models.
What remains unclear
The results are checked by the authors themselves, with no named third party. They depend on a per-attempt compute budget that this entry does not detail. The date is known only to the month.
1 source.
For experts
Sources(domains)
- primairearxiv.orglink only, reading not recorded
Method
Status “not evaluated” recorded on 11 October 2026 from arxiv.org (page read, quotation checked word for word).
Limits
A Lean proof supplied by the claimant does not count as formal verification by a third party. DiscoverIA has recorded no independent evaluation as of this date.
It is like a common exam: several models sit the same series of tests and one counts how many each passes.
Status history
Only one observation so far.
An observation is added; none is ever erased.
Report an error or suggest a source
Thank you, your message was sent.
Sending failed. Try again, or write to [email protected].