The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in language modeling.
☆146May 6, 2026Updated 3 months ago
Alternatives and similar repositories for llm-speedrunner
Users that are interested in llm-speedrunner are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- AIRA-dojo: a framework for developing and evaluating AI research agents☆157Apr 14, 2026Updated 4 months ago
- UQ: Assessing Language Models on Unsolved Questions☆30Aug 26, 2025Updated 11 months ago
- ☆15Mar 20, 2025Updated last year
- ☆153Oct 16, 2025Updated 9 months ago
- ☆28Sep 4, 2025Updated 11 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.
- ☆16Feb 22, 2026Updated 5 months ago
- Official Repository of Paper "Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs"☆15Sep 25, 2025Updated 10 months ago
- CIFAR-10 speedrun: Trains to 94% accuracy in 1.98 seconds on a single NVIDIA A100 GPU.☆79Jul 30, 2026Updated 2 weeks ago
- Simple & Scalable Pretraining for Neural Architecture Research☆342Mar 31, 2026Updated 4 months ago
- Pytorch routines for (Ker)nel (Mac)hines☆12Oct 10, 2025Updated 10 months ago
- Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent☆16Sep 8, 2022Updated 3 years ago
- ☆277Dec 2, 2024Updated last year
- Lab Cookbook☆41Aug 5, 2026Updated last week
- Agentic RL Training at Scale☆1,916Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Custom triton kernels for training Karpathy's nanoGPT.☆19Oct 21, 2024Updated last year
- Tinker ↔ KernelBench Integration enabling RL for GPU Kernel Generation☆30Mar 5, 2026Updated 5 months ago
- ☆15Sep 29, 2022Updated 3 years ago
- Production-Grade Autoresearch. Ideal for agent harness engineering, prompt engineering, ML model development, GPU kernels, and other opti…☆85Updated this week
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,485Apr 17, 2026Updated 3 months ago
- [ICML 2025] Code for "R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts"☆19Mar 10, 2025Updated last year
- Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours☆514Updated this week
- ☆130Jun 1, 2026Updated 2 months ago
- ☆25Oct 10, 2025Updated 10 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.
- See https://github.com/cuda-mode/triton-index/ instead!☆11May 8, 2024Updated 2 years ago
- Code for the paper: https://arxiv.org/pdf/2309.06979.pdf☆21Jul 29, 2024Updated 2 years ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆283Aug 5, 2026Updated last week
- Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike stat…☆543Updated this week
- A simple shellscript for splitting the PDF of a paper into the main body and an appendix.☆18Jun 1, 2020Updated 6 years ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆93Oct 30, 2024Updated last year
- ☆16Apr 26, 2023Updated 3 years ago
- Minimal and highly hackable implementation of Looped Transformers with GPT☆25Mar 8, 2026Updated 5 months ago
- The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".☆32Nov 12, 2024Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [NeurIPS '25] GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents☆90Jul 12, 2026Updated last month
- Ongoing research training transformer language models at scale, including: BERT☆16Apr 25, 2019Updated 7 years ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆231Nov 4, 2025Updated 9 months ago
- NanoGPT (124M) in 90 seconds☆5,668Updated this week
- ☆15Jun 19, 2026Updated last month
- RL models to play Sokoban. The fastest recipe wins.☆31Jul 25, 2026Updated 2 weeks ago
- Official code for NeurIPS 2025 paper "AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise"☆201Updated this week