# MMGR: Multi-Modal Generative Reasoning Benchmark and Evaluation

arXiv: https://arxiv.org/abs/2512.14691 · HTML: https://mlsanity.com/paper/2512.14691/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 33 of its 103 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 33)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [CLEVRER: CoLlision Events for Video REpresentation and Reasoning](https://mlsanity.com/paper/1910.01442/) (2019)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [Video models are zero-shot learners and reasoners](https://mlsanity.com/paper/2509.20328/) (2025)
- [WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2503.07265/) (2025)
- [On the Measure of Intelligence](https://mlsanity.com/paper/1911.01547/) (2019)
- [CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning](https://mlsanity.com/paper/1910.04744/) (2019)
- [General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping](https://mlsanity.com/paper/1907.05446/) (2019)
- [EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models](https://mlsanity.com/paper/2505.09694/) (2025)
- [Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark](https://mlsanity.com/paper/2510.26802/) (2025)
- [Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm](https://mlsanity.com/paper/2511.04570/) (2025)
- [T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation](https://mlsanity.com/paper/2508.17472/) (2025)
- [PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Models](https://mlsanity.com/paper/2406.11802/) (2024)
- [TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning](https://mlsanity.com/paper/2511.01833/) (2025)
- [A Configurable Library for Generating and Manipulating Maze Datasets](https://mlsanity.com/paper/2309.10498/) (2023)
- [textttComplex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark](https://mlsanity.com/paper/2504.13143/) (2025)
- [Sudoku-Bench: Evaluating creative reasoning with Sudoku variants](https://mlsanity.com/paper/2505.16135/) (2025)
- [WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation](https://mlsanity.com/paper/2505.01490/) (2025)
- [GIR-Bench: Versatile Benchmark for Generating Images with Reasoning](https://mlsanity.com/paper/2510.11026/) (2025)
- [NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistants](https://mlsanity.com/paper/2502.13894/) (2025)

## Built on by (most cited first, 12 of 12)

- [BabyVision: Visual Reasoning Beyond Language](https://mlsanity.com/paper/2601.06521/) (2026)
- [WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation](https://mlsanity.com/paper/2605.25874/) (2026)
- [Self-Refining Video Sampling](https://mlsanity.com/paper/2601.18577/) (2026)
- [Video Models Can Reason with Verifiable Rewards](https://mlsanity.com/paper/2605.15458/) (2026)
- [VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization](https://mlsanity.com/paper/2606.02564/) (2026)
- [CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models](https://mlsanity.com/paper/2605.08735/) (2026)
- [OpenCoF: Learning to Reason Through Video Generation](https://mlsanity.com/paper/2607.08763/) (2026)
- [Do multimodal models imagine electric sheep?](https://mlsanity.com/paper/2605.09693/) (2026)
- [Trimming the Long-Tail of Visual World Modeling Evaluation](https://mlsanity.com/paper/2606.24256/) (2026)
- [Thinking in Video: Can Video Generators Really Reason About the Real World?](https://mlsanity.com/paper/2607.17523/) (2026)
- [From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models](https://mlsanity.com/paper/2609.11242/) (2026)
- [MindTopo: Can Foundation Models Reason in Topological Space?](https://mlsanity.com/paper/2609.11900/) (2026)

## Abstract (arXiv)

Modern multimodal generative models can synthesize visually compelling images and videos, but it remains unclear whether this visual fluency reflects genuine reasoning: when prompted to generate a solution, can a model preserve the physical, logical, spatial, and temporal constraints a task requires, or does it merely produce plausible-looking media? To answer this question, we introduce MMGR (Multi-Modal Generative Reasoning Benchmark and Evaluation), a benchmark for evaluating generative reasoning across video, image, and language-based systems. MMGR covers 10 tasks from three domains (Abstract Reasoning, Embodied Navigation, and Physical Commonsense) and probes five reasoning abilities: Physical, Logical, 2D Spatial, 3D Spatial, and Temporal. Its evaluation emphasizes answer-verifiable tasks and, for video generation, process-aware chain-of-frame reasoning, where intermediate frames must form valid steps toward the target outcome rather than visually smooth but incorrect transitions. Evaluating state-of-the-art video generators, image generators, and LLM/VLM baselines reveals a sharp gap between visual quality and reasoning correctness: video models perform best on Physical Commonsense, but remain weak on symbolic tasks such as Sudoku, ARC, and Math, and brittle in cross-view embodied navigation. Image generators often outperform video generators on embodied navigation despite lacking temporal outputs, showing that longer visual generation does not automatically yield stronger reasoning. MMGR reframes evaluation of multimodal generation from whether outputs look realistic to whether they solve the underlying reasoning problem.