paper-with-me

홈 › Papers

SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?

2025-02-17 · Samuel Miserendino, Michele Wang, Tejal Patwardhan, Johannes Heidecke

We introduce SWE-Lancer, a benchmark of over 1,400 freelance software engineering tasks from Upwork, valued at \$1 million USD total in real-world payouts. SWE-Lancer encompasses both independent engineering tasks--ranging from \$50 bug fixes to \$32,000 feature implementations--and managerial tasks, where models choose between technical implementation proposals. Independent tasks are graded with end-to-end tests triple-verified by experienced software engineers, while managerial decisions are assessed against the choices of the original hired engineering managers. We evaluate model performance and find that frontier models are still unable to solve the majority of tasks. To facilitate future research, we open-source a unified Docker image and a public evaluation split, SWE-Lancer Diamond (https://github.com/openai/SWELancer-Benchmark). By mapping model performance to monetary value, we hope SWE-Lancer enables greater research into the economic impact of AI model development.

📄 PDF Abstract BibTeX arXiv:2502.12115

Code (1)

openai/swelancer-benchmark 공식 구현

Similar Papers 제목 키워드 기반

Can AI Freelancers Compete? Benchmarking Earnings, Reliability, and Task Success at Scale

2025-05-16 · David Noever, Forrest McKee

This study explores Large Language Models (LLMs) as autonomous agents for real-world tasks, including freelance software development. This work presents a new benchmark that evaluates LLMs on freelance programming and da…

BenchmarkingTAG

How Many Online Workers are there in the World? A Data-Driven Assessment

2021-03-23 · Otto Kässi, Vili Lehdonvirta, Fabian Stephany

An unknown number of people around the world are earning income by working through online labour platforms such as Upwork and Amazon Mechanical Turk. We combine data collected from various sources to build a data-driven …

Translation Analytics for Freelancers II: Benchmarking Local LLMs for Confidential Translation Workflows

2026-05-29 · Yuri Balashov, Rex VanHorn, Mingxi Xu, Austin Downes arxiv

Building on our previous work, this paper develops practical, low-barrier methods for freelance translators and smaller language service providers to evaluate translation technologies using rigorous yet accessible analyt…

Domain Adaptation

Can a Lightweight Multimodal Model Estimate LLM Reasoning Performance? A Study for Compute-Optimal Document Inference

2026-08-19 · Zishan Ahmad, Vishal Vaddina arxiv

Uniformly allocating inference reasoning budgets to LLMs is expensive and prone to over-thinking penalties; especially in document tasks where visual layouts drive complexity. To address this, we introduce BudgetDoc, the…

BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generation

2026-05-19 · Zijun Jia, Yuanchang Ye, Sen Jia, Yiyao Qian 외 arxiv

Large language models (LLMs) can enhance factuality via retrieval-augmented generation (RAG), but applying RAG to every query is unnecessary when the model-only answer is reliable. This motivates cascaded RAG: each query…

Open-Domain Question Answering