{"repo":"abundant-ai/swe-marathon","free":true,"listed":false,"github":"https://github.com/abundant-ai/swe-marathon","clone":"git clone https://github.com/abundant-ai/swe-marathon.git","description":"SWE-Marathon: an ultra long-horizon SWE benchmark","language":"Rust","stars":136,"topics":["benchmark","long-horizon","swe","terminal"],"license":"Apache-2.0","category":"cli-tools","readme_excerpt":"SWE-Marathon Can agents autonomously complete ultra-long-horizon software work? Links - Website - Paper - Leaderboard - Tasks News - [08/2026] ⭐ Featured on the GLM 5.3 model card! - [08/2026] ⚙️ Featured on the Grok 4.6 model card! - [07/2026] ➕ SWE-Marathon v1.1 is out with a fresh leaderboard! - [07/2026] 🌙 Featured on the Kimi K3 model card! - [07/2026] 🔥 Featured on the Grok 4.5 model card! - [06/2026] 🚀 Featured on the GLM 5.2 model card! Getting Started Install Harbor You also need - an Anthropic API key - a Modal account See scripts/run-benchmark.sh for the Harbor CLI commands to run trials with any model or harness. Downloading Logs SWE-Marathon trial logs are stored in a public S3 bucket of roughly 800 GB. Use this script to download trajectories. Message Rishi for S3 credentials. Citation License Apache License 2.0","default_branch":null,"files":null,"tree":[],"storefront":"/r/abundant-ai","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/abundant-ai/swe-marathon/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}