Alternatives and similar repositories for MageBench

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

• yihedeng9 / OpenVLThinker
  OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement
  ☆129Updated 6 months ago
• ASTRAL-Group / AlphaOne
  [EMNLP 2025 Main] AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
  ☆89Updated 7 months ago
• mbzuai-oryx / Agent-X
  Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
  ☆34Updated 2 months ago
• InfiXAI / InfiGUIAgent
  ☆73Updated 8 months ago
• microsoft / x-reasoner
  X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains
  ☆50Updated 8 months ago
• RUCAIBox / Virgo
  Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*
  ☆109Updated 8 months ago
• RifleZhang / LLaVA-Reasoner-DPO
  ☆110Updated last year
• xufangzhi / Genius
  [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework
  ☆71Updated 7 months ago
• Gabesarch / ICAL
  ☆51Updated 8 months ago
• ServiceNow / GroundCUA
  GroundCUA
  ☆65Updated last month
• InternScience / Dolphin
  (ACL-2025 main conference) Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback
  ☆38Updated 7 months ago
• orrzohar / Video-STaR
  [ICLR 2025] Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision
  ☆72Updated last year
• SalesforceAIResearch / LATTE
  ☆68Updated 4 months ago
• JiuTian-VL / Optimus-1
  [NeurIPS 2024] Official Implementation for Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
  ☆93Updated 7 months ago
• thu-nics / TaH
  Official implementation of paper "Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models"
  ☆64Updated 2 weeks ago
• callsys / GMPO
  [ICLR 2026] Geometric-Mean Policy Optimization
  ☆98Updated this week
• mathllm / MATH-V
  [NeurIPS 2024] MATH-Vision dataset and code to measure multimodal mathematical reasoning capabilities.
  ☆128Updated 8 months ago
• TIGER-AI-Lab / VL-Rethinker
  The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]
  ☆179Updated 7 months ago
• kokolerk / TON
  [NeurIPS 2025] Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
  ☆53Updated 4 months ago
• JIA-Lab-research / ARPO
  Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay
  ☆146Updated 8 months ago
• yuhui-zh15 / AutoConverter
  Official implementation of "Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation" (CVPR 202…
  ☆41Updated 8 months ago
• yannqi / R-4B
  The official repository of "R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Integration"
  ☆135Updated 4 months ago
• JieyuZ2 / TaskMeAnything
  [NeurIPS 2024] A task generation and model evaluation system for multimodal language models.
  ☆73Updated last year
• yunfeixie233 / ViGaL
  ☆64Updated 3 months ago
• Wang-ML-Lab / multimodal-needle-in-a-haystack
  [NAACL 2025 Oral] Multimodal Needle in a Haystack (MMNeedle): Benchmarking Long-Context Capability of Multimodal Large Language Models
  ☆54Updated 8 months ago
• njucckevin / MM-Self-Improve
  A Self-Training Framework for Vision-Language Reasoning
  ☆88Updated last year
• metal-chart-generation / metal
  ☆42Updated 8 months ago
• NuoJohnChen / JudgeLRM
  JudgeLRM: Large Reasoning Models as a Judge
  ☆40Updated last month
• CSfufu / Revisual-R1
  🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, multimodal rei…
  ☆193Updated last month
• VisualWebBench / VisualWebBench
  Evaluation framework for paper "VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?"
  ☆63Updated last year