---
type: "post"
id: "openai-s-math-solutions-aren-t-meeting-the-1fc6f6"
slug: "openai-s-math-solutions-aren-t-meeting-the-1fc6f6"
title: "OpenAI's math solutions aren't meeting the field's standards yet"
description: "TechCrunch reports that OpenAI released 719 manuscripts claiming solutions to difficult mathematics problems, while its process has drawn criticism from the Advisory Group on Mathematics and Artificial Intelligence (AGMAI) and other mathematicians."
retrieval_nugget: "TechCrunch reports that OpenAI released 719 manuscripts claiming solutions to difficult mathematics problems, while its process has drawn criticism from the Advisory Group on Mathematics and Artificial Intelligence (AGMAI) and other mathematicians."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["evals"]
entities: ["OpenAI","Advisory Group on Mathematics and Artificial Intelligence","Institute for Advanced Study","Lean","University of Cambridge","King's College London"]
related_patterns: ["scientific-agents-need-artifact-evidence","verification-bandwidth-is-the-scarce-resource"]
novelty_label: "new_angle"
what_changed: "The article argues OpenAI’s latest math proofs fell short of AGMAI’s standards for human understanding, highlighting concerns over proprietary-model testing and gaps between natural-language and formal proofs."
prior_refs: ["memory:ee4f13b0-3d4c-8475-a58c-4e99d18d64b1","memory:f7fad56a-8d83-834e-ad07-5afe397edcbb","memory:c057e04c-2d48-89d0-a833-52be35987378"]
source_url: "https://techcrunch.com/2026/10/08/openais-math-solutions-arent-meeting-the-fields-standards-yet"
source_urls: ["https://techcrunch.com/2026/10/08/openais-math-solutions-arent-meeting-the-fields-standards-yet"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:openai-s-math-solutions-aren-t-meeting-the-1fc6f6"
status: "published"
visuals: []
editor: {"role":"editor","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"]}
routes: {"html":"https://newruntime.com/posts/openai-s-math-solutions-aren-t-meeting-the-1fc6f6/","markdown":"https://newruntime.com/posts/openai-s-math-solutions-aren-t-meeting-the-1fc6f6.md","json":"https://newruntime.com/posts/openai-s-math-solutions-aren-t-meeting-the-1fc6f6.json"}
---

# OpenAI's math solutions aren't meeting the field's standards yet

## Retrieval answer

TechCrunch reports that OpenAI released 719 manuscripts claiming solutions to difficult mathematics problems, while its process has drawn criticism from the Advisory Group on Mathematics and Artificial Intelligence (AGMAI) and other mathematicians.

TechCrunch reports that OpenAI released 719 manuscripts claiming solutions to difficult mathematics problems, while its process has drawn criticism from the Advisory Group on Mathematics and Artificial Intelligence (AGMAI) and other mathematicians.

According to the report, only 10 of the 719 manuscripts included releases of model chain-of-thought material. It also says 42% of the released proofs had not undergone formalization. AGMAI’s guidance called for machine-readable metadata linking natural-language and formal artifacts; TechCrunch says OpenAI did not provide that correlation. The group’s first request was also that advanced open problems not be tested on proprietary models.

A paper by researchers at the University of Cambridge and King’s College London identified at least two discrepancies between a natural-language proof and Lean code for an OpenAI result derived from the Navier-Stokes equations. The authors say those discrepancies do not necessarily disprove either solution. The report does not establish that OpenAI’s mathematical claims are false, nor does it provide an independent review of every manuscript.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Evals](https://newruntime.com/topics/evals.md): Explore the evals topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)