[NeurIPS 2026] An ultra long-horizon SWE benchmark
☆177Nov 9, 2026Updated this week
Alternatives and similar repositories for swe-marathon
Users that are interested in swe-marathon are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Convert GitHub PRs into Harbor tasks☆90Jul 13, 2026Updated 3 months ago
- FrontierSWE is an ultra long-horizon coding agent benchmark that tests implementation, performance eng and ML research☆238Oct 22, 2026Updated 3 weeks ago
- Measuring and evolving with the frontier of agent work☆1,039Updated this week
- Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours☆620Updated this week
- open source SWE-Atlas☆89Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Pier is a Harbor fork built for DeepSWE, with stronger support for CLI agents in air-gapped (no-internet) tasks and more faithful, consis…☆228Oct 29, 2026Updated 2 weeks ago
- ☆46Oct 6, 2026Updated last month
- ☆32Jun 24, 2026Updated 4 months ago
- Measuring frontier coding agents on original, long-horizon engineering tasks☆1,899Aug 26, 2026Updated 2 months ago
- Science's Last Exam☆21Updated this week
- A compact high-signal benchmark for evaluating frontier agents☆45Aug 3, 2026Updated 3 months ago
- [NeurIPS 2026 Meta-Agents] PostTrainBench⁰ — Can LLM agents automate LLM post-training without gradients?☆17Sep 4, 2026Updated 2 months ago
- Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains☆880Updated this week
- Repository for results and data (coming soon!) for ClawsBench☆39Aug 28, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Research infra for creating RL environments, post-training, and evals.☆366Updated this week
- Can Language Models Rebuild Programs From Scratch?☆979Updated this week
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?☆559Sep 22, 2026Updated last month
- Spawn thousands of sub-agents in parallel☆14Aug 10, 2026Updated 3 months ago
- ☆60Updated this week
- RSI-Exam: Measuring Recursive Self-Improvement on Long-Horizon, Executable Research Tasks · Discord https://discord.gg/FBzhepyE☆195Updated this week
- A benchmark for evaluating AI agents on realistic business workflows☆388Aug 4, 2026Updated 3 months ago
- The first benchmark that asks code agents to build agents.☆25Jun 4, 2026Updated 5 months ago
- ☆193May 13, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆128Apr 1, 2026Updated 7 months ago
- EdgeBench: Unveiling scaling laws of learning from real-world environments☆477Updated this week
- Trajectory Recording and Capture Environments☆19Jan 24, 2026Updated 9 months ago
- ☆47May 16, 2026Updated 5 months ago
- ☆26Updated this week
- A benchmark for LLMs on complicated tasks in the terminal☆2,616Jul 11, 2026Updated 4 months ago
- LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering☆25Jun 2, 2026Updated 5 months ago
- A Difficulty-Calibrated Benchmark for Building Terminal Agents☆36Feb 20, 2026Updated 8 months ago
- ☆62May 3, 2026Updated 6 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A benchmark for evaluating how well AI coding agents can cooperate on software engineering tasks with potential conflicts.☆36Oct 18, 2026Updated 3 weeks ago
- ☆62May 21, 2025Updated last year
- Χ-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?☆76Updated this week
- SkillsBench evaluates how well skills work and how effective agents are at using them.☆1,915Updated this week
- 💻 SETA: Scaling Environments for Terminal Agents - Environments☆152Feb 16, 2026Updated 8 months ago
- A curated list of awesome Harbor ecosystem projects☆62May 29, 2026Updated 5 months ago
- Evaluating Long-Horizon Agentic Software Development Across Version Upgrades — 115 tasks, 17 repos, 5 languages☆18May 19, 2026Updated 5 months ago
Are these results useful?