# FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks

arXiv: https://arxiv.org/abs/2601.21165 · HTML: https://mlsanity.com/paper/2601.21165/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 8 of its 11 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 8 of 8)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models](https://mlsanity.com/paper/2307.10635/) (2023)
- [LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts](https://mlsanity.com/paper/2501.00274/) (2024)

## Built on by (most cited first, 30 of 47)

- [MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification](https://mlsanity.com/paper/2603.15726/) (2026)
- [Toward Generalist Autonomous Research via Hypothesis-Tree Refinement](https://mlsanity.com/paper/2606.11926/) (2026)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [LABBench2: An Improved Benchmark for AI Systems Performing Biology Research](https://mlsanity.com/paper/2604.09554/) (2026)
- [P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads](https://mlsanity.com/paper/2602.09443/) (2026)
- [Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction](https://mlsanity.com/paper/2605.13950/) (2026)
- [PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research](https://mlsanity.com/paper/2604.15411/) (2026)
- [Argus: Evidence Assembly for Scalable Deep Research Agents](https://mlsanity.com/paper/2605.16217/) (2026)
- [SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning](https://mlsanity.com/paper/2608.14277/) (2026)
- [ASI-Evolve: AI Accelerates AI](https://mlsanity.com/paper/2603.29640/) (2026)
- [Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions](https://mlsanity.com/paper/2606.02859/) (2026)
- [PRBench: End-to-end Paper Reproduction in Physics Research](https://mlsanity.com/paper/2603.27646/) (2026)
- [MATRIX: A Multimodal Benchmark and Post-Training Framework for Materials Science](https://mlsanity.com/paper/2602.00376/) (2026)
- [SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?](https://mlsanity.com/paper/2604.10718/) (2026)
- [Reliable Chain-of-Thought via Prefix Consistency](https://mlsanity.com/paper/2605.07654/) (2026)
- [ProjectionBench: Evaluating Scientific Hypothesis Generation in LLMs Under Progressive Information Disclosure](https://mlsanity.com/paper/2605.30284/) (2026)
- [Agents-K1: Towards Agent-native Knowledge Orchestration](https://mlsanity.com/paper/2606.13669/) (2026)
- [Parametric Skills](https://mlsanity.com/paper/2606.30015/) (2026)
- [Classroom Final Exam: An Instructor-Tested Reasoning Benchmark](https://mlsanity.com/paper/2602.19517/) (2026)
- [CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency](https://mlsanity.com/paper/2605.05873/) (2026)
- [Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning](https://mlsanity.com/paper/2605.06326/) (2026)
- [AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities](https://mlsanity.com/paper/2607.13705/) (2026)
- [TopoAgent: A Self-Evolving Topological Agent for Multimodal Scientific Reasoning](https://mlsanity.com/paper/2607.14658/) (2026)
- [What is Missing from AI Post-Training AI: An Empirical Analysis](https://mlsanity.com/paper/2608.19072/) (2026)
- [K-Bench: measuring model performance on real scientific agent requests](https://mlsanity.com/paper/2608.21601/) (2026)
- [Apodex 1.1: Scaling Agentic Intelligence for Complex Work](https://mlsanity.com/paper/2608.23283/) (2026)
- [Toward Evaluation Frameworks for Multi-Agent Scientific AI Systems](https://mlsanity.com/paper/2603.26718/) (2026)
- [COMPOSITE-Stem](https://mlsanity.com/paper/2604.09836/) (2026)
- [SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning](https://mlsanity.com/paper/2605.01489/) (2026)
- [Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals](https://mlsanity.com/paper/2605.23384/) (2026)

## Abstract (arXiv)

We introduce FrontierScience, a benchmark evaluating expert-level scientific reasoning in frontier language models. Recent model progress has nearly saturated existing science benchmarks, which often rely on multiple-choice knowledge questions or already published information. FrontierScience addresses this gap through two complementary tracks: (1) Olympiad, consisting of international olympiad problems at the level of IPhO, IChO, and IBO, and (2) Research, consisting of PhD-level, open-ended problems representative of sub-tasks in scientific research. FrontierScience contains several hundred questions (including 160 in the open-sourced gold set) covering subfields across physics, chemistry, and biology, from quantum electrodynamics to synthetic organic chemistry. All Olympiad problems are originally produced by international Olympiad medalists and national team coaches to ensure standards of difficulty, originality, and factuality. All Research problems are research sub-tasks written and verified by PhD scientists (doctoral candidates, postdoctoral researchers, or professors). For Research, we introduce a granular rubric-based evaluation framework to assess model capabilities throughout the process of solving a research task, rather than judging only a standalone final answer.