Alternatives and similar repositories for Physics

Users that are interested in Physics are comparing it to the libraries listed below

• GAIR-NLP / benbench
  Benchmarking Benchmark Leakage in Large Language Models
  ☆58Updated last year
• zitian-gao / SC-MCTS
  Interpretable Contrastive Monte Carlo Tree Search Reasoning
  ☆51Updated last year
• YangLing0818 / SuperCorrect-llm
  [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
  ☆87Updated 10 months ago
• facebookresearch / dualformer
  implementation of dualformer
  ☆24Updated 11 months ago
• lupantech / ineqmath
  Solving Inequality Proofs with Large Language Models.
  ☆56Updated last month
• HKUNLP / critic-rl
  [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning
  ☆120Updated 9 months ago
• mathllm / MathCoder2
  ☆71Updated last year
• hamishivi / automated-instruction-selection
  Exploration of automated dataset selection approaches at large scales.
  ☆52Updated 11 months ago
• SynthLabsAI / big-math
  A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models
  ☆72Updated 11 months ago
• Yu-Fangxu / FoR
  [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
  ☆120Updated last week
• mukhal / ThinkPRM
  Process Reward Models That Think
  ☆78Updated 2 months ago
• imagination-research / lbt
  [NeurIPS 2024] Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
  ☆59Updated last year
• THUDM / T1
  RL Scaling and Test-Time Scaling (ICML'25)
  ☆113Updated last year
• ozyyshr / StructChem
  Structured Chemistry Reasoning with Large Language Models
  ☆39Updated last year
• GAIR-NLP / OlympicArena
  [NeurIPS 2024] OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
  ☆107Updated 11 months ago
• TIGER-AI-Lab / TheoremQA
  The official repo for "TheoremQA: A Theorem-driven Question Answering dataset" (EMNLP 2023)
  ☆38Updated last year
• icip-cas / Verifier-Engineering
  Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
  ☆63Updated last year
• hkust-nlp / B-STaR
  B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
  ☆86Updated 8 months ago
• GAIR-NLP / MetaCritique
  Evaluate the Quality of Critique
  ☆36Updated last year
• Gen-Verse / CURE
  [NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
  ☆149Updated 4 months ago
• allenai / easy-to-hard-generalization
  Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"
  ☆48Updated 2 years ago
• Lagooon / LeanSTaR
  ☆42Updated last year
• LAMDASZ-ML / Self-Backtracking
  ☆52Updated last year
• ZonglinY / MOOSE
  [ACL 2024] <Large Language Models for Automated Open-domain Scientific Hypotheses Discovery>. It has also received the best poster award …
  ☆42Updated last year
• allenai / super-benchmark
  ☆49Updated 10 months ago
• kyegomez / Lets-Verify-Step-by-Step
  "Improving Mathematical Reasoning with Process Supervision" by OPENAI
  ☆114Updated last week
• mathllm / Step-Controlled_DPO
  ☆23Updated last year
• lqtrung1998 / mwp_cot_design
  ☆14Updated 2 years ago
• facebookresearch / llm-cross-capabilities
  Official implementation for "Law of the Weakest Link: Cross capabilities of Large Language Models"
  ☆43Updated last year
• QizhiPei / MathFusion
  MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion (ACL 2025)
  ☆35Updated 6 months ago