RepoOpenAIOpenAIpublished Feb 18, 2025seen 6d

openai/SWELancer-Benchmark

Open original ↗

Captured source

source ↗
published Feb 18, 2025seen 6dcaptured 12hhttp 200method plain

openai/SWELancer-Benchmark

Description: This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

Stars: 1439

Forks: 137

Open issues: 0

Created: 2025-02-18T17:23:15Z

Pushed: 2025-07-18T02:02:20Z

Default branch: main

Fork: no

Archived: yes

README:

SWELancer

The SWE-Lancer codebase has been merged into https://github.com/openai/preparedness!

Please see https://github.com/openai/preparedness to run SWELancer.

Notability

notability 7.0/10

Notable benchmark from OpenAI with solid traction.

OpenAI has a repo signal matching data demand, evals and quality.