Pith. sign in

REVIEW 7 cited by

Theoretical Physics Benchmark (TPBench) -- a Dataset and Study of AI Reasoning Capabilities in Theoretical Physics

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.15815 v1 pith:JLAK3KLT submitted 2025-02-19 cs.LG astro-ph.COcs.AIhep-phhep-th

Theoretical Physics Benchmark (TPBench) -- a Dataset and Study of AI Reasoning Capabilities in Theoretical Physics

classification cs.LG astro-ph.COcs.AIhep-phhep-th
keywords problemsmodelsphysicstheoreticalbenchmarkdatadatasetdifficulty
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce a benchmark to evaluate the capability of AI to solve problems in theoretical physics, focusing on high-energy theory and cosmology. The first iteration of our benchmark consists of 57 problems of varying difficulty, from undergraduate to research level. These problems are novel in the sense that they do not come from public problem collections. We evaluate our data set on various open and closed language models, including o3-mini, o1, DeepSeek-R1, GPT-4o and versions of Llama and Qwen. While we find impressive progress in model performance with the most recent models, our research-level difficulty problems are mostly unsolved. We address challenges of auto-verifiability and grading, and discuss common failure modes. While currently state-of-the art models are still of limited use for researchers, our results show that AI assisted theoretical physics research may become possible in the near future. We discuss the main obstacles towards this goal and possible strategies to overcome them. The public problems and solutions, results for various models, and updates to the data set and score distribution, are available on the website of the dataset tpbench.org.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark

    cs.AI 2025-09 unverdicted novelty 8.0

    CritPt benchmark shows state-of-the-art LLMs reach only 5.7% average accuracy on full-scale unpublished physics research tasks, rising to about 10% with coding tools.

  2. DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory

    cs.CR 2026-07 accept novelty 7.0

    A cheap symbolic consistency certificate for Seiberg-dual quiver pairs measurably improves LLM repair success, while the best budget-matched exploitation policy reverses between DeepSeek-Chat and Qwen-Plus.

  3. Fine-Tuning Small Reasoning Models for Quantum Field Theory

    cs.LG 2026-04 unverdicted novelty 7.0

    Small 7B reasoning models were fine-tuned on synthetic and curated QFT problems using RL and SFT, yielding performance gains, error analysis, and public release of data and traces.

  4. DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory

    cs.CR 2026-07 conditional novelty 6.0

    Verifier-gated LM repair improves success on broken quiver-gauge-theory claims, but the best exploitation policy reverses between deepseek-chat and qwen-plus.

  5. Towards Verifiable and Self-Correcting AI Physicists for Quantum Many-Body Simulations

    physics.comp-ph 2026-03 unverdicted novelty 6.0

    QMP-Bench supplies a realistic test set for AI on quantum many-body problems while PhysVEC uses integrated verifiers to turn unreliable LLM generations into code that passes both syntax and physics checks, outperformi...

  6. LLMs with in-context learning for Algorithmic Theoretical Physics

    cs.LG 2026-05 unverdicted novelty 5.0

    Frontier LLMs with in-context learning and CAS integration solve most algorithmic tasks in theoretical physics when supplied with worked examples.

  7. Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

    cs.AI 2025-03 unverdicted novelty 5.0

    The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.