LVLM-EHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models
Open accessThe DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Abstract
Large Vision-Language Models (LVLMs) have recently played a dominant role in multimodal vision-language learning. Despite the great success, it lacks a holistic evaluation of their efficacy. This paper presents a comprehensive evaluation of publicly available large multimodal models by building an LVLM evaluation Hub (LVLM-eHub). Our LVLM-eHub consists of 13 representative LVLMs such as InstructBLIP and LLaVA, which are thoroughly evaluated by a quantitative capability evaluation and an online arena platform. The former evaluates five categories of multimodal capabilities of LVLMs such as visual question answering and object hallucination on 42 in-domain text-related visual benchmarks, while the latter provides the user-level evaluation of LVLMs in an open-world question-answering scenario. The study investigates how specific features of LVLMs such as model configurations, modality alignment mechanisms, and training data affect the multimodal understanding. By conducting a comprehensive comparison of these features on quantitative and arena evaluation, our study uncovers several innovative findings, which establish a fundamental framework for the development and evaluation of innovative strategies aimed at enhancing multimodal techniques. Our LVLM-eHub is available at https://github.com/OpenGVLab/Multi-Modality-Arena.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Are we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897 · cited 1×
“Automated evaluation is widely used in various fields, including natural language processing [44], [45], [46], [47], computer vision [48], [49], [50], [51], reinforcement learning [52], [53], [54], [55], and others, due to its convenience and reliability in many aspects.”
The Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · cited 1×
“Automated evaluation is widely used in various fields, including natural language processing [44], [45], [46], [47], computer vision [48], [49], [50], [51], reinforcement learning [52], [53], [54], [55], and others, due to its convenience and reliability in many aspects.”
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.-J., Shamma, D. A., et al. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-016-0981-7 · Cited by 5,107 · cited 1×
“OurLVLM-eHubconsistsof13representative Index Terms —Vision-language model, multimodal evaluation, large language model, multi-turn evaluation.”
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222
Automated Flower Classification over a Large Number of Classes
Nilsback, M.-E., & Zisserman, A. (2008) · 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing · doi:10.1109/icvgip.2008.47 · Cited by 3,442 · cited 2×
“We evaluate this capability of models through image classification (ImgCLs) using the ImageNet1K [26], CIFAR10 [27], Pets37 [28] and Flowers102 [29] benchmarks, multi-class identification (MCI) and object counting (OC) using the GVT [30] benchmark.”
A large annotated corpus for learning natural language inference
Bowman, S. R., Angeli, G., Potts, C., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1075 · Cited by 3,377 · cited 1×
“Automated evaluation is widely used in various fields, including natural language processing [44], [45], [46], [47], computer vision [48], [49], [50], [51], reinforcement learning [52], [53], [54], [55], and others, due to its convenience and reliability in many aspects.”
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
Williams, A., Nangia, N., & Bowman, S. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1101 · Cited by 3,342
Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1516 · Cited by 2,428
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E. P., et al. (2023) · arXiv · doi:10.48550/arxiv.2306.05685 · Cited by 1,888 · cited 1×
“Arena Results: We ranked the selected 10 LVLMs using the Elo rating [100] based on our collected data, following the methodology outlined in Fastchat [101], [102].”
Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning
Sharma, P., Ding, N., Goodman, S., & Soricut, R. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1238 · Cited by 1,879 · cited 1×
“OurLVLM-eHubconsistsof13representative Index Terms —Vision-language model, multimodal evaluation, large language model, multi-turn evaluation.”
Li, J., Li, D., Xiong, C., & Hoi, S. (2022) · arXiv · doi:10.48550/arxiv.2201.12086 · Cited by 1,741
Microsoft COCO Captions: Data Collection and Evaluation Server
Chen, X., Fang, H., Lin, T.-Y., Vedantam, R., Gupta, S., Dollar, P., & Zitnick, C. L. (2015) · arXiv · doi:10.48550/arxiv.1504.00325 · Cited by 1,614 · cited 1×
“OurLVLM-eHubconsistsof13representative Index Terms —Vision-language model, multimodal evaluation, large language model, multi-turn evaluation.”
Flamingo: a Visual Language Model for Few-Shot Learning
Alayrac, J.-B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.14198 · Cited by 1,555
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441
DINOv2: Learning Robust Visual Features without Supervision
Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.07193 · Cited by 1,078
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
Li, C., Wong, C., Zhang, S., Usuyama, N., Liu, H., Yang, J., Naumann, T., Poon, H., & Gao, J. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1240 · Cited by 986
Li, J., Li, D., Savarese, S., & Hoi, S. (2023) · arXiv · doi:10.48550/arxiv.2301.12597 · Cited by 908 · cited 4×
“Third , we find that Otter-Image, BLIVA, and BLIP2 cannot follow the user’s instructions well and generate wrong reasoning steps sometimes, They attain a much worse ranking in the arena than quantitative evaluation because responses with hallucination would have a negative influence on user experience.”
InfluentialFrom Recognition to Cognition: Visual Commonsense Reasoning
Zellers, R., Bisk, Y., Farhadi, A., & Choi, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00688 · Cited by 769 · cited 1×
“To evaluate this capability, we test the model’s understanding of commonly shared human knowledge about generic visual concepts usingbenchmarks suchas ImageNetVC[16] andvisual commonsense reasoning (VCR) [85].”
Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023) · arXiv · doi:10.48550/arxiv.2304.08485 · Cited by 682
MMBench: Is Your Multi-modal Model an All-Around Player?
Liu, Y., Duan, H., Zhang, Y., Li, B., Zhang, S., Zhao, W., Yuan, Y., Wang, J., He, C., Liu, Z., et al. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72658-3_13 · Cited by 668
VizWiz: nearly real-time answers to visual questions
Bigham, J. P., Jayant, C., Ji, H., Little, G., Miller, A., Miller, R. C., Miller, R., Tatarowicz, A., White, B., White, S., et al. (2010) · Proceedings of the 23nd annual ACM symposium on User interface software and technology · doi:10.1145/1866029.1866080 · Cited by 601 · cited 1×
“For KGID, we use ScienceQA IMG [84] and VizWiz [37].”
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
Li, C., Wong, C., Zhang, S., Usuyama, N., Liu, H., Yang, J., Naumann, T., Poon, H., & Gao, J. (2023) · arXiv · doi:10.48550/arxiv.2306.00890 · Cited by 590 · cited 2×
“This methodsimplifiesthealignmentofimageandtextfeatures withinthesamesemanticspace,anditseffectivenesshasbeen demonstratedbyLLaVA[7].”
MMBench: Is Your Multi-modal Model an All-around Player?
Liu, Y., Duan, H., Zhang, Y., Li, B., Zhang, S., Zhao, W., Yuan, Y., Wang, J., He, C., Liu, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.06281 · Cited by 487
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Zhu, D., Chen, J., Shen, X., Li, X., & Elhoseiny, M. (2023) · arXiv · doi:10.48550/arxiv.2304.10592 · Cited by 469 · cited 5×
“Moreover, MiniGPT-4 demonstrates that even a small fine-tuning set can efficiently restore the distortions in language generation that may arise from the alignment process.”
InfluentialMeta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
Yu, T., Quillen, D., He, Z., Julian, R., Narayan, A., Shively, H., Bellathur, A., Hausman, K., Finn, C., & Levine, S. (2019) · arXiv · doi:10.48550/arxiv.1910.10897 · Cited by 450
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Bai, Y., Jones, A., Ndousse, K., Askell, A., Chen, A., DasSarma, N., Drain, D., Fort, S., Ganguli, D., Henighan, T., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.05862 · Cited by 442 · cited 1×
“Furthermore, we rank the selected 8 LVLMs with Elo rating [79] using two copies of the collected data by following Fastchat [62] and [80].”
MMMU: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
Yue, X., Ni, Y., Zheng, T., Zhang, K., Liu, R., Zhang, G., Stevens, S., Jiang, D., Ren, W., Sun, Y., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00913 · Cited by 429 · cited 1×
“Comparative analysis shows that InternVL2-40B outperforms GPT-4V and Gemini Pro 1.5 in the MM-Bench [20] and OpenCompass benchmarks [62], while maintaining comparable performance in MMMU [40].”
InfluentialSelf-citationLAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs
Schuhmann, C., Vencu, R., Beaumont, R., Kaczmarczyk, R., Mullis, C., Katta, A., Coombes, T., Jitsev, J., & Komatsuzaki, A. (2021) · arXiv · doi:10.48550/arxiv.2111.02114 · Cited by 358
Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., & Duan, N. (2023) · arXiv · doi:10.48550/arxiv.2303.04671 · Cited by 197 · cited 1×
“One notable advancement in this direction is the groundbreaking Visual ChatGPT [34], which has successfully enabled LLMs to process multimodal inputs by leveraging a variety of tools.”
Leveraging Procedural Generation to Benchmark Reinforcement Learning
Cobbe, K., Hesse, C., Hilton, J., & Schulman, J. (2019) · arXiv · doi:10.48550/arxiv.1912.01588 · Cited by 196
Peng, B., Li, C., He, P., Galley, M., & Gao, J. (2023) · arXiv · doi:10.48550/arxiv.2304.03277 · Cited by 183
Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning
Gupta, A., Kumar, V., Lynch, C., Levine, S., & Hausman, K. (2019) · arXiv · doi:10.48550/arxiv.1910.11956 · Cited by 153 · cited 2×
“Furthermore, in the Appendix C, we present quantitative evaluation results for Franka Kitchen [61], Minecraft [59], and Meta-World [78].”
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images
Bitton-Guetta, N., Bitton, Y., Hessel, J., Schmidt, L., Elovici, Y., Stanovsky, G., & Schwartz, R. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00247 · Cited by 37
Cited by
MMBench: Is Your Multi-modal Model an All-Around Player?
Liu, Y., Duan, H., Zhang, Y., Li, B., Zhang, S., Zhao, W., Yuan, Y., Wang, J., He, C., Liu, Z., et al. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72658-3_13 · Cited by 668
MMBench: Is Your Multi-modal Model an All-around Player?
Liu, Y., Duan, H., Zhang, Y., Li, B., Zhang, S., Zhao, W., Yuan, Y., Wang, J., He, C., Liu, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.06281 · Cited by 487
MMMU: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
Yue, X., Ni, Y., Zheng, T., Zhang, K., Liu, R., Zhang, G., Stevens, S., Jiang, D., Ren, W., Sun, Y., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00913 · Cited by 429
“More holistic evaluations have been conducted as well, such as LAMM [76], LVLM-eHub [72], SEED [30], MMBench [43], and MM-Vet [79].”
MethodSelf-citationMVBench: A Comprehensive Multi-modal Video Understanding Benchmark
Li, K., Wang, Y., He, Y., Li, Y., Wang, Y., Liu, Y., Wang, Z., Xu, J., Chen, G., Lou, P., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.02095 · Cited by 300
Self-citationSpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
Chen, B., Xu, Z., Kirmani, S., Ichter, B., Sadigh, D., Guibas, L., & Xia, F. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01370 · Cited by 281
Metadata
- Authors
- Xu, P., Shao, W., Zhang, K., Gao, P., Liu, S., Lei, M., Meng, F., Huang, S., Qiao, Y., & Luo, P.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2025-03
- Volume
- 47
- Issue
- 3
- Pages
- 1877-1893
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W4404788931
- Cited by
- 99
- References
- 36
- FWCI
- 13.56
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.