SWE-Marathon: an ultra long-horizon SWE benchmark
☆103Jul 13, 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:
- open source SWE-Atlas☆51Updated this week
- FrontierSWE is an ultra long-horizon coding agent benchmark that tests implementation, performance eng and ML research☆174Updated this week
- Measuring agents' ability to get work done on a computer☆308Updated this week
- Convert GitHub PRs into Harbor tasks☆69Updated this week
- ☆18Jun 18, 2026Updated 3 weeks 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.
- Pier is a Harbor fork built for DeepSWE, with stronger support for CLI agents in air-gapped (no-internet) tasks and more faithful, consis…☆110Updated this week
- Repository for results and data (coming soon!) for ClawsBench☆30Apr 8, 2026Updated 3 months ago
- An agent for auditing repositories of traces for violations of safety properties. Automatically finds cheating (task-level gaming and har…☆15Jun 6, 2026Updated last month
- Can Language Models Rebuild Programs From Scratch?☆846Updated this week
- Benchmarking execution environments ability to prevent reward hacking in agent evals.☆15Jun 18, 2026Updated 3 weeks ago
- Measuring frontier coding agents on original, long-horizon engineering tasks☆1,116Updated this week
- Official Repository of paper MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Pol…☆69Jan 26, 2026Updated 5 months ago
- Terminal-Bench 2.1☆40Updated this week
- 💻 SETA: Scaling Environments for Terminal Agents - Environments☆141Feb 16, 2026Updated 4 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.
- ☆81Jun 25, 2026Updated 2 weeks ago
- A benchmark for evaluating AI agents on realistic business workflows☆128Jul 7, 2026Updated last week
- MCP Atlas☆116Updated this week
- ☆28Jun 1, 2026Updated last month
- A compact high-signal benchmark for evaluating frontier agents☆15Updated this week
- ☆60May 21, 2025Updated last year
- Implementation for IceCache: Memory-Efficient KV-cache Management for Long-Sequence LLMs (ICLR 2026).☆19Jun 9, 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 2 years ago
- Agents' Last Exam☆853Updated this week
- 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.
- An implementation of a device tracking technique based on Algorithm 4 (Double-Hash Port Selection) of RFC 6056.☆16Sep 28, 2022Updated 3 years ago
- SWE-Together: Evaluating Coding Agents in Interactive User Sessions☆41Jul 7, 2026Updated last week
- [Roadmap] Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling☆124Jun 9, 2026Updated last month
- New testbed of interactive SWE tasks for coding agents, set in a realistic multi-turn developer driven environment☆17Jun 30, 2026Updated 2 weeks ago
- AI agent benchmark hackability scanner — find evaluation vulnerabilities before they undermine your results☆40May 25, 2026Updated last month
- Advances and Frontiers of LLM-based Issue Resolution in Software Engineering A Comprehensive Survey☆86Apr 22, 2026Updated 2 months ago
- [NeurIPS '25] GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents☆85Updated this week
- Dataset of hackable TerminalBench-style tasks and exploit trajectories☆31Apr 18, 2026Updated 2 months ago
- Official repository Flash Local Linear Attention☆37May 28, 2026Updated last month
- 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.
- OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks☆187Updated this week
- ☆143May 13, 2026Updated 2 months ago
- 🌟 SwarmAgent: A framework for simulating social group dynamics using multi-agent collaboration, aiding insights into collective behavior…☆13Dec 5, 2023Updated 2 years ago
- ☆12Dec 17, 2023Updated 2 years ago
- Multi-agent synthetic data generation pipeline capable of generating and validating long horizon terminal/coding tasks for RL training☆70Jul 28, 2025Updated 11 months ago
- Download Web-10K data by querying Bing Image Search☆10Feb 1, 2022Updated 4 years ago
- Data recipes and robust infrastructure for training AI agents☆259Updated this week