# COMPOSITE-Stem

arXiv: https://arxiv.org/abs/2604.09836 · HTML: https://mlsanity.com/paper/2604.09836/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 6 of 6)

- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks](https://mlsanity.com/paper/2510.04374/) (2025)
- [FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks](https://mlsanity.com/paper/2601.21165/) (2026)
- [APEX-Agents](https://mlsanity.com/paper/2601.14242/) (2026)

## Built on by (most cited first, 1 of 1)

- [Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation](https://mlsanity.com/paper/2609.11115/) (2026)

## Abstract (arXiv)

AI agents hold growing promise for accelerating scientific discovery; yet, a lack of frontier evaluations hinders adoption into real workflows. Expert-written benchmarks have proven effective at measuring AI reasoning, but most at this stage have become saturated and only measure performance on constrained outputs. To help address this gap, we introduce COMPOSITE-STEM, a benchmark of 70 expert-written tasks in physics, biology, chemistry, and mathematics, curated by doctoral-level researchers. Our benchmark combines exact-match grading and criterion-based rubrics with an LLM-as-a-jury grading protocol, allowing more flexible assessment of scientifically meaningful outputs. Using an adapted multimodal Terminus-2 agent harness within the Harbor agentic evaluation framework, we evaluate four frontier models. The top-performing model achieves 21%, demonstrating that COMPOSITE-STEM captures capabilities beyond current agent reach. All tasks are open-sourced with contributor permission to support reproducibility and to promote additional research towards AI's acceleration of scientific progress in these domains.