Dr Gabriela Calistro Rivera accepted the prize on behalf of CosmoAmautas at the congress and delivered a public lecture describing the association’s work, giving the international planetary science community a detailed look at how a volunteer-driven programme can achieve national scale in a country with pronounced geographic and infrastructural inequalities. In presenting the award on behalf of Europlanet, Thibaut Roger highlighted the association’s distinctive approach, noting that the organisation has demonstrated how rural schools can be supported to become places where planetary science and astronomy are not only explained but actively and sustainably practised, citing as an example the search for exoplanets using real observational data in the classroom.

The scale of what CosmoAmautas has accomplished since its founding in 2021 is considerable by any measure of science outreach. The association has trained more than 200 teachers across 21 of Peru’s 24 regions, a coverage footprint that spans the Pacific desert coast, the high Andean plateaus and the edge of the Amazon basin. Those teachers, in turn, have carried the programme’s activities to more than 10,000 students, and the association has supported the creation and operation of more than 80 Astroclubs, extracurricular groups in which school pupils continue to explore astronomy well beyond the formal timetable. This multiplier strategy, investing in teachers rather than attempting to reach students directly one by one, is the structural core of the project and the reason its reach has grown so rapidly with comparatively modest resources.

The pedagogical philosophy underpinning the programme is inquiry-based learning, an approach that positions students as investigators rather than recipients of facts. Rather than memorising that the Earth rotates or that the planets orbit the Sun, students in CosmoAmautas activities measure the Earth’s rotation and dimensions themselves, replicating in spirit the classical geometric methods used since antiquity to determine the size of our planet. They build and interrogate scale models of the Solar System, confronting firsthand the counterintuitive emptiness of interplanetary space and the true ratios of planetary sizes and orbital distances. They also analyse data returned by real space missions, an exercise that introduces them to the actual workflows of professional planetary scientists, from data cleaning and calibration to interpretation and error estimation.

Perhaps the most technically ambitious strand of the programme is its classroom-based exoplanet research. Using real data, students participate in the search for planets orbiting other stars, a field that has exploded since the 1990s into one of the most active areas of modern astronomy. The detection method most accessible to schools relies on photometry, the precise measurement of a star’s brightness over time. When a planet crosses the face of its host star from our line of sight, a transit, it blocks a tiny fraction of the starlight, producing a characteristic dip in the light curve. Detecting such dips requires careful measurement, patience and an understanding of systematic noise, skills that map directly onto the scientific method itself. By entrusting school students with genuine datasets rather than sanitised demonstrations, CosmoAmautas communicates something that textbooks alone rarely can: that cutting-edge discovery is not reserved for observatories in wealthy countries but is a process anyone with data, curiosity and guidance can join.

A defining feature of the association is its deliberate integration of Andean ancestral astronomical traditions into its curriculum. Peru’s cultural history contains a deep and sophisticated relationship with the sky, from the agricultural calendars of Andean communities to the astronomical alignments of pre-Columbian civilisations. By weaving these traditions into modern lessons, CosmoAmautas makes two arguments at once: that observing and interpreting the sky are deeply rooted in Peru’s cultural history, and that contemporary science is not a foreign import to be passively received but a continuation of a conversation Andean communities have been having with the cosmos for centuries. This framing matters for inclusion. Students who might otherwise perceive astronomy as the cultural property of distant nations instead encounter it as part of their own inheritance, a connection that educators widely recognise as a powerful predictor of engagement and persistence in scientific fields.

Gender equality and inclusion are stated core values of the association, and they shape how its resources are designed and distributed. The team has developed a range of teaching materials explicitly adapted to schools with limited infrastructure, a pragmatic acknowledgement that many Peruvian schools lack laboratories, reliable internet or even consistent electricity. The resources are linked to the Peruvian national curriculum, so that teachers can deploy them without sacrificing mandated content, and they are delivered through three complementary channels: physical experiment boxes, printed guides and online materials. The experiment boxes deserve particular attention as a piece of low-cost engineering in their own right, packaging hands-on activities so that a teacher with no specialised equipment can still run genuine measurements. The printed guides ensure that the programme functions where connectivity fails, while the online materials allow continuous support and updating for teachers who do have access.

The human infrastructure of CosmoAmautas is as distinctive as its pedagogy. The team is composed of Peruvian students and astronomy professionals living both in Peru and across the globe, working in all fields of astronomy and planetary sciences. This diaspora model converts the common reality of scientific emigration from Latin America into an asset, allowing researchers based in Europe, North America and elsewhere to contribute remotely to science education in their home country. Because the communities the association most wants to reach are underserved and often geographically isolated, its initiatives have so far taken place mainly online, a format that proved its value during the pandemic years and continues to offer reach at low cost. The organisation’s future plans, however, include in-person events, and the Europlanet prize funding will partially support this expansion into direct, face-to-face engagement, which outreach practitioners generally regard as uniquely valuable for building lasting relationships with schools and communities.

For Calistro Rivera, the meaning of the award is captured in the name of the organisation itself. Amauta means teacher in Quechua, the most widely spoken indigenous language of the Andes, and the programme is founded on the principle that when a teacher is empowered, the future of an entire community can be transformed. In her remarks upon receiving the prize, she described the honour as belonging not only to the CosmoAmautas team but to the wider community of teachers and students across Peru who have carried the programme’s activities into their classrooms, and she framed the award as an incentive to continue bringing scientific education and access to astronomy to more regions and more students in the country. That framing reflects a theory of change that has been validated by the association’s own growth: a relatively small core of professional and student volunteers, multiplied through hundreds of trained teachers, can achieve a reach that direct intervention alone never could.

The Europlanet Prize for Public Engagement, awarded annually by the Europlanet Society, exists precisely to spotlight work of this kind, in which the practice of planetary science is extended beyond research institutions into society. CosmoAmautas joins a lineage of recognised projects that have demonstrated creative, sustainable ways of widening participation in space science, and its selection signals the growing recognition within the European planetary community that engagement must be global and that the most effective models are often those built locally, in the languages, landscapes and cultural traditions of the communities they serve. With a national footprint already spanning nearly the whole of Peru, a proven teacher-training pipeline, and new funding to take its work into in-person settings, the association enters its next phase with a simple and compelling proposition: that the next generation of Peruvian astronomers may first look up from a rural classroom, guided by an empowered teacher, holding a box of experiments and a light curve from a distant star.

Subject of Research: Recognition of a Peruvian astronomy and planetary science education outreach programme through the Europlanet Prize for Public Engagement

Article Title: Europlanet Prize for Public Engagement 2026 awarded to CosmoAmautas

Article References: Europlanet Prize for Public Engagement 2026 awarded to CosmoAmautas. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: CosmoAmautas, Europlanet, science outreach, astronomy education, Peru, public engagement, exoplanets, inquiry-based learning, teacher training, Andean astronomy, EPSC2026, STEM education

The findings come from a systematic benchmark of five state-of-the-art large language models on examinations from the International Olympiad on Astronomy and Astrophysics, or IOAA. Unlike conventional AI tests that ask short factual questions, the Olympiad papers require students to combine physics, mathematics and astronomy across multiple stages of reasoning. Problems may involve deriving equations, interpreting physical systems, analyzing observations and translating a diagram or image into a quantitative solution. The exams therefore provide a more demanding test of whether an AI system can reason through astronomy rather than simply recall astronomical facts.

Researchers evaluated the models on four IOAA theory examinations held between 2022 and 2025, as well as on data-analysis examinations. The theory papers are designed to probe the foundations of astrophysics, including mechanics, gravitation, radiation, celestial coordinates and the behavior of astronomical systems. Solving such problems generally requires more than applying a familiar formula. A model must identify the relevant physical assumptions, select a mathematical approach, follow a chain of deductions and check whether the final result is consistent with the situation described.

Two models stood out in the theoretical tests. Gemini 2.5 Pro achieved an average score of 85.6 percent across the four examinations, while GPT-5 reached 84.2 percent. Those results placed both systems at a level comparable to, or higher than, the strongest students in examination groups of approximately 200 to 300 participants. According to the researchers, the scores fall within the range typically associated with gold-medal performance, suggesting that frontier AI systems can now handle many Olympiad-style astronomy problems with a degree of competence once associated only with elite human competitors.

The result is particularly significant because Olympiad problems are not ordinary classroom exercises. They often conceal the essential physics inside a complicated description, requiring the solver to decide what can be neglected and what must be retained. A successful solution may depend on recognizing a symmetry, selecting an appropriate reference frame, interpreting a limiting case or connecting an observed quantity to an underlying physical parameter. In this setting, a correct answer is evidence of substantial problem-solving ability, even when the model reaches it through a different internal process than a human student.

Yet high average scores do not mean that the models have mastered astronomy in a general sense. Performance varied substantially from problem to problem, and the researchers’ error analysis identified recurring weaknesses across all of the systems. Conceptual reasoning, geometric reasoning and spatial visualization remained difficult, with accuracy in these categories ranging from roughly 52 to 79 percent. These failures are important because they can appear even when a model knows the relevant equations. An AI may reproduce a familiar formula correctly but misunderstand the physical arrangement of objects, confuse an angle or distance, or apply an equation outside the conditions in which it is valid.

Spatial reasoning is especially central to astronomy. Many astronomical systems cannot be examined directly and must instead be reconstructed from projected images, changing brightness, apparent motion or the relative positions of objects on the sky. A diagram may represent a three-dimensional orbit in two dimensions, while an observation may encode information about inclination, orientation or line-of-sight motion. To solve the problem, a system must build an internal geometric model and manipulate it consistently. The benchmark suggests that language-based competence and symbolic calculation do not automatically provide this capacity.

The contrast became sharper on the data-analysis examinations. GPT-5 achieved an average score of 88.5 percent, a performance comparable to that of top-ten human participants. Other models scored considerably lower, with average results ranging from 48 to 76 percent. Data-analysis tests typically require candidates to extract patterns from tables, plots or observational measurements, estimate uncertainties and connect empirical trends to an astrophysical explanation. They can expose weaknesses that remain hidden in text-only reasoning, because a model must first identify what the data represent before it can calculate or interpret anything.

This divergence between models and examination types shows why simple benchmark scores can be misleading. An AI system may perform exceptionally well on carefully formatted theoretical questions yet struggle when information is distributed across a figure, a graph and a written description. Even when a model can process images, multimodal input does not guarantee reliable scientific interpretation. The system must understand scales, axes, coordinate systems, units, uncertainties and the physical meaning of a visual pattern. A small misreading at the beginning of the analysis can propagate through every subsequent calculation and produce an answer that appears mathematically polished but is scientifically wrong.

The study therefore presents a mixed picture of AI’s future in astronomy. On one hand, the leading models have demonstrated an extraordinary ability to perform multistep derivations and answer advanced theoretical questions at near-elite human levels. They could become useful assistants for checking calculations, explaining standard methods, exploring alternative solutions or helping researchers navigate established knowledge. On the other hand, autonomous research requires more than solving isolated examination problems. Scientific agents must decide which questions are meaningful, design analyses, recognize ambiguous evidence, track uncertainty and detect when their assumptions have failed. The Olympiad results indicate that these capabilities cannot be inferred from high scores alone.

For astronomy, the distinction matters because modern research increasingly depends on complex, multimodal evidence. Telescopes generate images, spectra, time series and catalogs containing millions of measurements. A research assistant that can manipulate equations but misinterprets geometry could draw the wrong conclusion about an orbit, a stellar population or the structure of a distant galaxy. Likewise, a system that produces confident explanations without recognizing uncertainty could make errors difficult to detect. The researchers’ conclusion is not that LLMs are incapable of scientific reasoning, but that their current strengths are unevenly distributed and that critical gaps remain before they can operate as autonomous astronomers.

The benchmark offers a new way to measure those gaps. By moving beyond short factual questions and testing derivation, multimodal interpretation and sustained reasoning, it brings AI evaluation closer to the realities of scientific work. The gold-medal-level theory scores show how rapidly language models have advanced. The weaker and more variable results in conceptual, geometric and data-driven tasks show why headline performance must be treated cautiously. The next generation of astronomy AI will need not only broader knowledge and better calculation, but also stronger spatial models, more dependable physical intuition and the ability to recognize when an apparently elegant solution does not describe the universe.

Subject of Research: Large language models’ performance on advanced astronomy and astrophysics examinations.

Article Title: Gold-medal performance by LLMs at the International Olympiad on Astronomy and Astrophysics

Article References: Carrit Delgado Pinheiro, L., Chen, Z., Caixeta Piazza, B. et al. “Gold-medal performance by LLMs at the International Olympiad on Astronomy and Astrophysics.” Nature Astronomy (2026). https://doi.org/10.1038/s41550-026-02964-w

Image Credits: AI Generated

DOI: https://doi.org/10.1038/s41550-026-02964-w

Keywords: large language models, artificial intelligence, astronomy, astrophysics, International Olympiad on Astronomy and Astrophysics, Gemini 2.5 Pro, GPT-5, multimodal reasoning, scientific AI, spatial visualization