MMMU-Pro is a stricter multimodal benchmark that removes text-only solvable questions, augments options, and requires reading text from images, yielding substantially lower model scores of 16.8-26.9%.
hub
MMBench: Is Your Multi-modal Model an All-around Player?
32 Pith papers cite this work. Polarity classification is still indexing.
32
Pith papers citing it
abstract
Large vision-language models (VLMs) have recently achieved remarkable progress, exhibiting impressive multimodal perception and reasoning abilities. However, effectively evaluating these large VLMs remains a major challenge, hindering future development in this domain. Traditional benchmarks like VQAv2 or COCO Caption provide quantitative performance measurements but lack fine-grained ability assessment and robust evaluation metrics. Meanwhile, subjective benchmarks, such as OwlEval, offer comprehensive evaluations of a model's abilities by incorporating human labor, which is not scalable and may display significant bias. In response to these challenges, we propose MMBench, a bilingual benchmark for assessing the multi-modal capabilities of VLMs. MMBench methodically develops a comprehensive evaluation pipeline, primarily comprised of the following key features: 1. MMBench is meticulously curated with well-designed quality control schemes, surpassing existing similar benchmarks in terms of the number and variety of evaluation questions and abilities; 2. MMBench introduces a rigorous CircularEval strategy and incorporates large language models to convert free-form predictions into pre-defined choices, which helps to yield accurate evaluation results for models with limited instruction-following capabilities. 3. MMBench incorporates multiple-choice questions in both English and Chinese versions, enabling an apples-to-apples comparison of VLMs' performance under a bilingual context. To summarize, MMBench is a systematically designed objective benchmark for a robust and holistic evaluation of vision-language models. We hope MMBench will assist the research community in better evaluating their models and facilitate future progress in this area. The evalutation code of MMBench has been integrated into VLMEvalKit: https://github.com/open-compass/VLMEvalKit.
hub tools
citation-role summary
dataset 2
citation-polarity summary
roles
dataset 2polarities
use dataset 2representative citing papers
GazeVLM introduces internal gaze tokens that allow VLMs to dynamically suppress irrelevant visual features and simulate foveal attention for improved high-resolution multimodal reasoning.
Medical VLMs frequently select negated options that contradict visible chest X-ray findings, achieving only ~30% accuracy on direct presence probes, but a post-hoc consistency verifier raises accuracy above 95%.
XTC-Bench reveals that strong performance on generation or understanding tasks in unified multimodal models does not guarantee cross-task semantic consistency, which instead depends on how tightly coupled the learning objectives are across modalities.
ShredBench shows state-of-the-art MLLMs perform well on intact documents but suffer sharp drops in restoration accuracy as fragmentation increases to 8-16 pieces, indicating insufficient cross-modal semantic reasoning for VRDU.
MLVU is a new benchmark for long video understanding that uses extended videos across diverse genres and multi-task evaluations, revealing that current MLLMs struggle significantly and degrade sharply with longer durations.
SEED-Bench is a new benchmark of 19K multiple-choice questions for evaluating generative comprehension in multimodal LLMs across 12 image and video dimensions.
GRIP-VLM applies group-relative policy optimization via reinforcement learning to prune visual tokens in VLMs, yielding up to 15% inference speedup at matched accuracy over prior methods.
LVLMs show vocabulary hijacking by inert tokens that decode to hijacking anchors; HABI locates them, NHAR finds resilient heads, and HAVAE boosts those heads to cut hallucinations.
Stronger VLM agents use mirror reflections for self-identification in controlled 3D tests, while weaker ones inspect but fail to extract or correctly attribute self-relevant information.
VisMMoE exploits visual-expert affinity via token pruning to achieve up to 2.68x faster VL-MoE inference on memory-constrained hardware while keeping accuracy competitive.
Evaluator VLMs frequently fail to detect quality-degrading perturbations in I2T and T2I outputs, with failure rates exceeding 50% in some cases.
MACS improves inference speed in multimodal MoE models by entropy-weighted balancing of visual tokens and real-time modality-adaptive expert capacity allocation.
Modality-native routing in A2A networks raises task accuracy from 32% to 52% over text-bottleneck baselines on a 50-task benchmark, but only when paired with capable downstream reasoning.
Equitable attention via Dominant Object Penalty and Outlier Boost Coefficient reduces object hallucinations in multimodal LLMs without retraining.
CLEAR uses degradation-aware fine-tuning, a latent representation bridge, and interleaved reinforcement learning to connect generative and reasoning capabilities in multimodal models for better degraded image understanding.
InternVL3.5 advances open-source multimodal models with Cascade RL for +16% reasoning gains and ViR for 4x inference speedup, with the 241B model reaching SOTA among open-source MLLMs on multimodal, reasoning, and agentic tasks.
GLM-4.5V reaches state-of-the-art results on 42 multimodal benchmarks among open-source models of similar size by applying reinforcement learning with curriculum sampling to a strong vision foundation model.
InternVL3-78B sets a new open-source SOTA of 72.2 on MMMU via native joint multimodal pre-training, V2PE, MPO, and test-time scaling while remaining competitive with proprietary models.
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
Emu3 shows that next-token prediction on a unified discrete token space for text, images, and video lets a single transformer outperform task-specific models such as SDXL and LLaVA-1.6 in multimodal generation and perception.
Current LVLM benchmarks overestimate capabilities because many questions can be answered without images due to design flaws or data leakage; MMStar is a human-curated set of 1,500 vision-indispensable samples across 6 capabilities and 18 axes with new metrics for leakage and true multi-modal gain.
A new 1.2M-caption dataset generated via GPT-4V improves LMMs on MME and MMBench by 222.8/22.0/22.3 and 2.7/1.3/1.5 points respectively when used for supervised fine-tuning.
Video-LLaVA creates a unified visual representation for images and videos via pre-projection alignment, enabling mutual enhancement from joint training and strong results on image and video benchmarks.
citing papers explorer
-
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
MMMU-Pro is a stricter multimodal benchmark that removes text-only solvable questions, augments options, and requires reading text from images, yielding substantially lower model scores of 16.8-26.9%.
-
GazeVLM: Active Vision via Internal Attention Control for Multimodal Reasoning
GazeVLM introduces internal gaze tokens that allow VLMs to dynamically suppress irrelevant visual features and simulate foveal attention for improved high-resolution multimodal reasoning.
-
CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs
Medical VLMs frequently select negated options that contradict visible chest X-ray findings, achieving only ~30% accuracy on direct presence probes, but a post-hoc consistency verifier raises accuracy above 95%.
-
Beyond Accuracy: Benchmarking Cross-Task Consistency in Unified Multimodal Models
XTC-Bench reveals that strong performance on generation or understanding tasks in unified multimodal models does not guarantee cross-task semantic consistency, which instead depends on how tightly coupled the learning objectives are across modalities.
-
ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction
ShredBench shows state-of-the-art MLLMs perform well on intact documents but suffer sharp drops in restoration accuracy as fragmentation increases to 8-16 pieces, indicating insufficient cross-modal semantic reasoning for VRDU.
-
MLVU: Benchmarking Multi-task Long Video Understanding
MLVU is a new benchmark for long video understanding that uses extended videos across diverse genres and multi-task evaluations, revealing that current MLLMs struggle significantly and degrade sharply with longer durations.
-
SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
SEED-Bench is a new benchmark of 19K multiple-choice questions for evaluating generative comprehension in multimodal LLMs across 12 image and video dimensions.
-
GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models
GRIP-VLM applies group-relative policy optimization via reinforcement learning to prune visual tokens in VLMs, yielding up to 15% inference speedup at matched accuracy over prior methods.
-
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination
LVLMs show vocabulary hijacking by inert tokens that decode to hijacking anchors; HABI locates them, NHAR finds resilient heads, and HAVAE boosts those heads to cut hallucinations.
-
Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All?
Stronger VLM agents use mirror reflections for self-identification in controlled 3D tests, while weaker ones inspect but fail to extract or correctly attribute self-relevant information.
-
VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading
VisMMoE exploits visual-expert affinity via token pruning to achieve up to 2.68x faster VL-MoE inference on memory-constrained hardware while keeping accuracy competitive.
-
Seeing Isn't Believing: Uncovering Blind Spots in Evaluator Vision-Language Models
Evaluator VLMs frequently fail to detect quality-degrading perturbations in I2T and T2I outputs, with failure rates exceeding 50% in some cases.
-
MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference
MACS improves inference speed in multimodal MoE models by entropy-weighted balancing of visual tokens and real-time modality-adaptive expert capacity allocation.
-
Modality-Native Routing in Agent-to-Agent Networks: A Multimodal A2A Protocol Extension
Modality-native routing in A2A networks raises task accuracy from 32% to 52% over text-bottleneck baselines on a 50-task benchmark, but only when paired with capable downstream reasoning.
-
See Fair, Speak Truth: Equitable Attention Improves Grounding and Reduces Hallucination in Vision-Language Alignment
Equitable attention via Dominant Object Penalty and Outlier Boost Coefficient reduces object hallucinations in multimodal LLMs without retraining.
-
CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models
CLEAR uses degradation-aware fine-tuning, a latent representation bridge, and interleaved reinforcement learning to connect generative and reasoning capabilities in multimodal models for better degraded image understanding.
-
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
InternVL3.5 advances open-source multimodal models with Cascade RL for +16% reasoning gains and ViR for 4x inference speedup, with the 241B model reaching SOTA among open-source MLLMs on multimodal, reasoning, and agentic tasks.
-
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
GLM-4.5V reaches state-of-the-art results on 42 multimodal benchmarks among open-source models of similar size by applying reinforcement learning with curriculum sampling to a strong vision foundation model.
-
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
InternVL3-78B sets a new open-source SOTA of 72.2 on MMMU via native joint multimodal pre-training, V2PE, MPO, and test-time scaling while remaining competitive with proprietary models.
-
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
-
Emu3: Next-Token Prediction is All You Need
Emu3 shows that next-token prediction on a unified discrete token space for text, images, and video lets a single transformer outperform task-specific models such as SDXL and LLaVA-1.6 in multimodal generation and perception.
-
Are We on the Right Way for Evaluating Large Vision-Language Models?
Current LVLM benchmarks overestimate capabilities because many questions can be answered without images due to design flaws or data leakage; MMStar is a human-curated set of 1,500 vision-indispensable samples across 6 capabilities and 18 axes with new metrics for leakage and true multi-modal gain.
-
ShareGPT4V: Improving Large Multi-Modal Models with Better Captions
A new 1.2M-caption dataset generated via GPT-4V improves LMMs on MME and MMBench by 222.8/22.0/22.3 and 2.7/1.3/1.5 points respectively when used for supervised fine-tuning.
-
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
Video-LLaVA creates a unified visual representation for images and videos via pre-projection alignment, enabling mutual enhancement from joint training and strong results on image and video benchmarks.
-
MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
MME is a manually annotated benchmark evaluating MLLMs on perception and cognition across 14 subtasks to avoid data leakage and support fair model comparisons.
-
Multilingual Training and Evaluation Resources for Vision-Language Models
Releases regenerated multilingual training data and translated benchmarks for VLMs in five languages and demonstrates consistent benefits from multilingual training over English-only baselines.
-
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
BLIP3-o uses a diffusion transformer to generate CLIP image features and a sequential pretraining strategy to build open models that perform strongly on both image understanding and generation benchmarks.
-
MiniCPM-V: A GPT-4V Level MLLM on Your Phone
MiniCPM-Llama3-V 2.5 delivers GPT-4V-level multimodal performance on phones through architecture, pretraining, and alignment optimizations.
-
Semantic Reality: Interactive Context-Aware Visualization of Inter-Object Relationships in Augmented Reality
Semantic Reality maintains a persistent connectivity graph of objects in AR via multimodal reasoning and action recognition, then visualizes relationships to aid understanding and task guidance.
-
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
InternVL 1.5 narrows the performance gap to proprietary multimodal models via a stronger transferable vision encoder, dynamic high-resolution tiling, and curated English-Chinese training data.
-
Improved Baselines with Visual Instruction Tuning
Simple changes to LLaVA using CLIP-ViT-L-336px, an MLP connector, and academic VQA data yield state-of-the-art results on 11 benchmarks with only 1.2M public examples and one-day training on 8 A100 GPUs.
-
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
Scaling data, model size, and training optimization on the Janus architecture yields better multimodal understanding and more stable, instruction-following text-to-image generation.