# CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction

arXiv: https://arxiv.org/abs/2604.25399 · HTML: https://mlsanity.com/paper/2604.25399/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 15 of 15)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement](https://mlsanity.com/paper/2511.23475/) (2025)
- [Balancing Fidelity and Plasticity: Aligning Mixed-Precision Fine-Tuning with Linguistic Hierarchies](https://mlsanity.com/paper/2505.03802/) (2025)
- [QPruner: Probabilistic Decision Quantization for Structured Pruning in Large Language Models](https://mlsanity.com/paper/2412.11629/) (2024)
- [textttReMind: Understanding Deductive Code Reasoning in LLMs](https://mlsanity.com/paper/2511.00488/) (2025)

## Built on by (most cited first, 2 of 2)

- [Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark](https://mlsanity.com/paper/2609.28449/) (2026)
- [Complexity-Aware Evaluation of LLM Comprehension](https://mlsanity.com/paper/2609.37405/) (2026)

## Abstract (arXiv)

Despite strong performance on code generation tasks, it remains unclear whether large language models (LLMs) genuinely reason about code execution. Existing code reasoning benchmarks primarily evaluate final output correctness under a single canonical implementation, leaving two critical aspects underexplored: (1) whether LLMs can maintain consistency to functionally equivalent implementations, and (2) whether LLMs can accurately reason about intermediate execution states. We introduce CoRE, a Code Reasoning benchmark that evaluates code reasoning through implementation invariance and process transparency. Extensive evaluations on eight frontier LLMs reveal two fundamental limitations. First, models exhibit a substantial robustness gap, with performance varying significantly across equivalent implementations. Second, we observe superficial execution, where models arrive at correct final outputs without correctly reasoning about intermediate execution states. Together, these findings demonstrate that output-only evaluations are insufficient for assessing code reasoning and position CoRE as a necessary benchmark for evaluating robust and faithful code reasoning.footnoteData and code are available at https://github.com/ZJUSig/CoRE.