OneAstronomy improves astronomy benchmark performance

Zhejiang Lab and NAOC report that OneAstronomy outperformed comparison models on astronomy benchmarks. Discoveries and public benefits remain unmeasured.

AI system

System

OneAstronomy

Model

Not assessed

Release

Not assessed

Application developer

Zhejiang Lab and National Astronomical Observatories of China

Role

Not assessed

Configuration

Not assessed

Inputs and outputs

Not assessed

Autonomy

Not assessed

Workflow

Conditions that could produce the benefit are unspecified.

Human oversight

Not assessed

Relation to AI

Domain-specific training and retrieval support astronomical reasoning and analysis. The developers report stronger benchmark performance. New scientific discoveries are unreported.

AI contribution

Domain-specific training and retrieval support astronomical reasoning and analysis. The developers report stronger benchmark performance. New scientific discoveries are unreported.

Benefits

Outcome identifiers

Not assessed

Benefit

Zhejiang Lab and NAOC report that OneAstronomy outperformed comparison models on astronomy benchmarks. Discoveries and public benefits remain unmeasured.

Category

Improved Task Accuracy

Status

Reported and intended benefits

Beneficiary groups

Organizations. People. Society.

Beneficiaries

Not assessed

Reach

Not assessed

Distribution and access

Not assessed

Duration

Not assessed

Expected?

Yes

Costs and harms

Not assessed

Measurement

Studies

Not assessed

Study design

Not assessed

Measurement

Not assessed

Setting and sample

Not assessed

Measures

Not assessed

Comparison

Not assessed

Results

Not assessed

Additional value from AI

Not assessed

Limitations

Not assessed

Denominators

Not assessed

Materials for replication

Not assessed

Money

Kind of value

Not assessed

Amount

Not assessed

Currency and prices

Not assessed

Period and unit

Not assessed

Realization

Not assessed

Recipients and payers

Not assessed

Gross or net

Not assessed

Included costs

Not assessed

Comparison

Not assessed

Method

Not assessed

Return and payback

Not assessed

People and places

Participants

Developer: Zhejiang Lab and National Astronomical Observatories of China.

Jurisdictions

Not assessed

Ownership and control

Not assessed

Dependencies

Not assessed

Cross-border connections

Not assessed

Geopolitical implications

Not assessed

Follow-up

Conditions for replication

Domain-specific astronomical corpora and benchmark tasks.

Replication attempts

Not assessed

Later findings

Not assessed

Availability

Not assessed

Institutional decision

Not assessed

Grounds

Not assessed

Action and result

Not assessed

Success criterion

Not assessed

Evidence

Source numbers

AIBD-0514-source-0001

Citations

Numbered references below.

Language

Not assessed

Source relationships

Developer

Original evidence

Not assessed

Access and versions

Not assessed

Supported findings

Not assessed

Evidence strength

Not assessed

Missing evidence

Not assessed

Grades

Assessed benefits

Organizations. People. Society.

Depth

Organizations: 2. People: Not assessed. Society: Not assessed.

Reasons

Organizations: The authors report that OneAstronomy outperformed comparison models on astronomy knowledge and reasoning benchmarks. This is a research-tool capability gain, not evidence of new astronomical discoveries. People: Wider public access to astronomy learning is intended, with no learning impact measured. Society: Space-weather protection and scientific public benefits remain prospective.

Observed or intended

Reported and intended benefits

Rubric

Not assessed

Assessor and date

Not assessed

Alternative assessments

Not assessed

Fill

The makers' claim

Entry details

Kind

Not assessed

Field

Smart home/cities.

Purpose

Support astronomical reasoning, analysis, and access to domain knowledge.

Dates

Source information as of: June 2025. Updated: 22 October 2026.

Stage

Not assessed

Version

SHA-256: 9238946209aa…

References

Other identifiers

ITU AI for Good: Innovate for Impact (2025). ITU-131.

Category mappings

Not assessed

Brief

Not assessed

Revisions

1 revisions. Latest: 22 October 2026.

Sources

  1. Report Developer

    Project account in International Telecommunication Union, AI for Good: Innovate for Impact, 2025. Information current as of June 2025. Outcomes are reported by the project team. The account provides no independent outcome evaluation.