ProgramBench finds no model can fully rebuild software from scratch
zetalyrae · x · 2026-07-25
ProgramBench tests whether models can rebuild software from scratch
A screenshot shows the paper “ProgramBench: Can Language Models Rebuild Programs From Scratch?” and notes that hashcards was included in the study.
The paper’s premise is that current benchmarks often test narrow tasks like fixing a single bug or adding one feature, but real software work requires something broader: designing and implementing an entire codebase from a program plus documentation.
Key points from the paper shown in the image:
- Agents must match the behavior of a reference executable, not just produce code that looks plausible.
- End-to-end behavioral tests are generated via agent-driven fuzzing.
- The benchmark includes 200 tasks, spanning small CLI tools to real software like FFmpeg, SQLite, and the PHP interpreter.
- The authors evaluate 9 LMs and report that none fully solve any task; the best model passes 95% of tests on only 3% of tasks.
- Models tend to prefer monolithic, single-file implementations that diverge sharply from human-written code.
The image also lists eudoxia0/hashcards as a plain-text spaced repetition flashcard system, suggesting it was one of the software targets used in the benchmark.
More from coding & agent
- 250 Builders Hack With Codex at Berlin Community Hackathon Ahead of OpenAI DevDay — paw_lean · 2026-10-26
- Building AI bots on raw APIs? Devs say models are 'dumb without the harness' — madeofAjala · 2026-10-26
- HarnessMM cuts agent tokens per task by up to 88% while raising success rates — omarsar0 · 2026-10-26
- Microsoft demos intent-classifying agents built with Copilot App and Foundry, deployable across Teams and Outlook — marlene_zw · 2026-10-26
- Looking for a wearable mic with best battery life that feeds recordings to personal agents via MCP — altryne · 2026-10-26
- The identity crisis in software engineering: multiagent systems demand a new problem set — rakyll · 2026-10-26