CompMat-Bench: Benchmarking AI Agents for Computational Materials Science

arXiv:2610.00636 · cs.AI, cond-mat.mtrl-sci, cs.LG · Submitted 2026-09-30 · Read on arXiv

cs.AI, cond-mat.mtrl-sci, cs.LG

Submitted: 2026-09-30

Updated: 2026-10-15

Code: https://github.com/openai/codex

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• AI Agents — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes

Sources

• MDArena: Evaluating Coding Agents on Realistic Molecular Dynamics Workflows
• Quantum Computing Technology Roadmaps and Capability Assessment for Scientific Computing -- An analysis of use cases from the NERSC workload
• SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs
• Evaluating Large Language Models Trained on Code
• ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
• DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
• Towards Verifiable and Self-Correcting AI Physicists for Quantum Many-Body Simulations
• Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction
• Measuring Massive Multitask Language Understanding
• TritonDFT: Automating DFT with a Multi-Agent Framework
• Can Coding Agents Reproduce Findings in Computational Materials Science?
• gwBenchmarks: Stress-Testing LLM Agents on High-Precision Gravitational Wave Astronomy
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• MDGYM: Benchmarking AI Agents on Molecular Simulations
• MatTools: Benchmarking Large Language Models for Materials Science Tools
• The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
• OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts
• PRBench: End-to-end Paper Reproduction in Physics Research
• INCARBench: A Benchmark for Scientific Configuration in VASP INCAR by Large Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems