SWE-Marathon: an ultra long-horizon SWE benchmark
☆152Sep 10, 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☆83Jul 13, 2026Updated 2 months ago
- FrontierSWE is an ultra long-horizon coding agent benchmark that tests implementation, performance eng and ML research☆229Aug 13, 2026Updated last month
- Measuring and evolving with the frontier of agent work☆673Updated 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☆554Updated this week
- ☆23Jun 18, 2026Updated 2 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains☆571Updated this week
- ☆41May 16, 2026Updated 3 months ago
- Framework for evaluating and improving agents☆5,158Updated this week
- ☆20Aug 9, 2026Updated last month
- Research infra for creating RL environments, post-training, and evals.☆345Updated this week
- Pier is a Harbor fork built for DeepSWE, with stronger support for CLI agents in air-gapped (no-internet) tasks and more faithful, consis…☆188Aug 29, 2026Updated 2 weeks ago
- ☆61May 21, 2025Updated last year
- Repository for results and data (coming soon!) for ClawsBench☆34Aug 28, 2026Updated 2 weeks ago
- 💻 SETA: Scaling Environments for Terminal Agents - Environments☆146Feb 16, 2026Updated 6 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- An easy-to-use manual to use the OpenBB terminal developed by 3 university students☆10Dec 11, 2022Updated 3 years ago
- Can Language Models Rebuild Programs From Scratch?☆924Updated this week
- A curated list of awesome Harbor ecosystem projects☆52May 29, 2026Updated 3 months ago
- New testbed of interactive SWE tasks for coding agents, set in a realistic multi-turn developer driven environment☆26Jun 30, 2026Updated 2 months ago
- ☆173May 13, 2026Updated 4 months ago
- ☆145Mar 31, 2026Updated 5 months ago
- Academic papers and works related to SWE-bench and SWE-agents☆16Dec 8, 2025Updated 9 months ago
- ☆122Apr 1, 2026Updated 5 months ago
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?☆522May 18, 2026Updated 3 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- A Difficulty-Calibrated Benchmark for Building Terminal Agents☆30Feb 20, 2026Updated 6 months ago
- Benchmark harness and code for "SWE-fficiency: Can Language Models Optimize Real World Repositories on Real World Workloads?"☆25Feb 17, 2026Updated 6 months ago
- [NeurIPS '25] GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents☆91Jul 12, 2026Updated 2 months ago
- Agent application/benchmark/workload traces should be placed here.☆15Apr 13, 2026Updated 5 months ago
- A benchmark for evaluating AI agents on realistic business workflows☆279Aug 4, 2026Updated last month
- [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents☆765Updated this week
- A benchmark for LLMs on complicated tasks in the terminal☆2,576Jul 11, 2026Updated 2 months ago
- Official Repository for "Training Versatile Coding Agents in Synthetic Environments"☆22Jan 11, 2026Updated 8 months ago
- MCP Atlas☆153Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- A compact high-signal benchmark for evaluating frontier agents☆37Aug 3, 2026Updated last month
- [ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution☆482Aug 18, 2026Updated 3 weeks ago
- ☆82Jun 25, 2026Updated 2 months ago
- Harbor dataset for Senior SWE-Bench (v2026.06)☆54Jul 8, 2026Updated 2 months ago
- Trajectory Recording and Capture Environments☆19Jan 24, 2026Updated 7 months ago
- SkillsBench evaluates how well skills work and how effective agents are at using them.☆1,764Jul 23, 2026Updated last month
- This repository contains the official implementation for the ECCV'22 paper, "SPIN: An Empirical Evaluation on Sharing Parameters of Isotr…☆20Sep 9, 2023Updated 3 years ago