RewardBench: the first evaluation tool for reward models.
☆713Feb 16, 2026Updated 2 months ago
Alternatives and similar repositories for reward-bench
Users that are interested in reward-bench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Recipes to train reward model for RLHF.☆1,531Apr 24, 2025Updated last year
- A recipe for online RLHF and online iterative DPO.☆544Dec 28, 2024Updated last year
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,441Updated this week
- Scalable toolkit for efficient model alignment☆853Oct 6, 2025Updated 7 months ago
- Robust recipes to align language models with human and AI preferences☆5,593Apr 8, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆163Nov 23, 2024Updated last year
- Reference implementation for DPO (Direct Preference Optimization)☆2,888Aug 11, 2024Updated last year
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,982Aug 9, 2025Updated 9 months ago
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆904Sep 30, 2025Updated 7 months ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆953Feb 16, 2025Updated last year
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,840Jun 17, 2025Updated 10 months ago
- 800,000 step-level correctness labels on LLM solutions to MATH problems☆2,128Jun 1, 2023Updated 2 years ago
- Arena-Hard-Auto: An automatic LLM benchmark.☆1,018Jun 21, 2025Updated 10 months ago
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,600Nov 24, 2025Updated 5 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A large-scale, fine-grained, diverse preference dataset (and models).☆366Dec 29, 2023Updated 2 years ago
- AllenAI's post-training codebase☆3,708May 3, 2026Updated last week
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆844Jul 1, 2024Updated last year
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,745Jan 8, 2024Updated 2 years ago
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,239May 8, 2024Updated 2 years ago
- Train transformer language models with reinforcement learning.☆18,282Updated this week
- GenRM-CoT: Data release for verification rationales☆68Oct 16, 2024Updated last year
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,408Apr 11, 2024Updated 2 years ago
- Official Repo for Open-Reasoner-Zero☆2,093Jun 2, 2025Updated 11 months ago
- 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.
- ☆315Jun 9, 2024Updated last year
- O1 Replication Journey☆2,000Jan 14, 2025Updated last year
- ☆1,137Jan 10, 2026Updated 4 months ago
- A framework for few-shot evaluation of language models.☆12,411Apr 30, 2026Updated last week
- Simple RL training for reasoning☆3,853Dec 23, 2025Updated 4 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆702Jan 20, 2025Updated last year
- Official repository for ACL 2025 paper "ProcessBench: Identifying Process Errors in Mathematical Reasoning"☆190May 20, 2025Updated 11 months ago
- Directional Preference Alignment☆61Sep 23, 2024Updated last year
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,046Apr 30, 2026Updated last 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.
- [NIPS2023] RRHF & Wombat☆806Sep 22, 2023Updated 2 years ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆593Dec 9, 2024Updated last year
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"☆41Sep 24, 2024Updated last year
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,358Dec 9, 2025Updated 5 months ago
- Generative Judge for Evaluating Alignment☆250Jan 18, 2024Updated 2 years ago
- ☆284Jan 6, 2025Updated last year
- Scalable RL solution for advanced reasoning of language models☆1,852Mar 18, 2025Updated last year