L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Execution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Simeng, Hsieh, Cheng-Ping, Ladhak, Faisal, Arakelyan, Erik, Serano, Santiago Akle, Ginsburg, Boris
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910908833333248
author Sun, Simeng
Hsieh, Cheng-Ping
Ladhak, Faisal
Arakelyan, Erik
Serano, Santiago Akle
Ginsburg, Boris
author_facet Sun, Simeng
Hsieh, Cheng-Ping
Ladhak, Faisal
Arakelyan, Erik
Serano, Santiago Akle
Ginsburg, Boris
contents Complex reasoning tasks often rely on the ability to consistently and accurately apply simple rules across incremental steps, a foundational capability which we term "level-0" reasoning. To systematically evaluate this capability, we introduce L0-Bench, a language model benchmark for testing procedural correctness -- the ability to generate correct reasoning processes, complementing existing benchmarks that primarily focus on outcome correctness. Given synthetic Python functions with simple operations, L0-Bench grades models on their ability to generate step-by-step, error-free execution traces. The synthetic nature of L0-Bench enables systematic and scalable generation of test programs along various axes (e.g., number of trace steps). We evaluate a diverse array of recent closed-source and open-weight models on a baseline test set. All models exhibit degradation as the number of target trace steps increases, while larger models and reasoning-enhanced models better maintain correctness over multiple steps. Additionally, we use L0-Bench to explore test-time scaling along three dimensions: input context length, number of solutions for majority voting, and inference steps. Our results suggest substantial room to improve "level-0" reasoning and potential directions to build more reliable reasoning systems.
format Preprint
id arxiv_https___arxiv_org_abs_2503_22832
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Execution
Sun, Simeng
Hsieh, Cheng-Ping
Ladhak, Faisal
Arakelyan, Erik
Serano, Santiago Akle
Ginsburg, Boris
Programming Languages
Computation and Language
Complex reasoning tasks often rely on the ability to consistently and accurately apply simple rules across incremental steps, a foundational capability which we term "level-0" reasoning. To systematically evaluate this capability, we introduce L0-Bench, a language model benchmark for testing procedural correctness -- the ability to generate correct reasoning processes, complementing existing benchmarks that primarily focus on outcome correctness. Given synthetic Python functions with simple operations, L0-Bench grades models on their ability to generate step-by-step, error-free execution traces. The synthetic nature of L0-Bench enables systematic and scalable generation of test programs along various axes (e.g., number of trace steps). We evaluate a diverse array of recent closed-source and open-weight models on a baseline test set. All models exhibit degradation as the number of target trace steps increases, while larger models and reasoning-enhanced models better maintain correctness over multiple steps. Additionally, we use L0-Bench to explore test-time scaling along three dimensions: input context length, number of solutions for majority voting, and inference steps. Our results suggest substantial room to improve "level-0" reasoning and potential directions to build more reliable reasoning systems.
title L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Execution
topic Programming Languages
Computation and Language
url https://arxiv.org/abs/2503.22832