Papers › PECC: Problem Extraction and Coding Challenges

PECC: Problem Extraction and Coding Challenges

29 Apr 2024arXiv:2404.18766archive 2025-07-28

Patrick Haller, Jonas Golde, Alan Akbik

Recent advancements in large language models (LLMs) have showcased their exceptional abilities across various tasks, such as code generation, problem-solving and reasoning. Existing benchmarks evaluate tasks in isolation, yet the extent to which LLMs can understand prose-style tasks, identify the underlying problems, and then generate appropriate code solutions is still unexplored. Addressing this gap, we introduce PECC, a novel benchmark derived from Advent Of Code (AoC) challenges and Project Euler, including 2396 problems. Unlike conventional benchmarks, PECC requires LLMs to interpret narrative-embedded problems, extract requirements, and generate executable code. A key feature of our dataset is the complexity added by natural language prompting in chat-based evaluations, mirroring real-world instruction ambiguities. Results show varying model performance between narrative and neutral problems, with specific challenges in the Euler math-based subset with GPT-3.5-Turbo passing 50% of the AoC challenges and only 8% on the Euler problems. By probing the limits of LLMs' capabilities, our benchmark provides a framework to monitor and assess the subsequent progress of LLMs as a universal problem solver.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

hallerpatrick/pecc officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Code GenerationMathText Generation

Datasets

Introduced by this paper, per the archive.

PECC

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Code Generation PECC Claude 3 Haiku Pass@3 27.67 #1 of 8 Archive leaderboard report
Code Generation PECC GPT-3.5 Turbo Pass@3 23.75 #2 of 8 Archive leaderboard report
Code Generation PECC codechat-bison Pass@3 11.39 #3 of 8 Archive leaderboard report
Code Generation PECC chat-bison Pass@3 8.48 #4 of 8 Archive leaderboard report
Code Generation PECC Mixtral-8x7B-Instruct Pass@3 8.35 #5 of 8 Archive leaderboard report
Code Generation PECC Phi-3-mini-128k-instruct Pass@3 7.18 #6 of 8 Archive leaderboard report
Code Generation PECC WizardLM-2-7B Pass@3 3.72 #7 of 8 Archive leaderboard report
Code Generation PECC Llama-3-8B-Instruct Pass@3 3.1 #8 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections