Papers › Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text...

Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

24 Aug 2023arXiv:2308.12966archive 2025-07-28

Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, Jingren Zhou

In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models (LVLMs) designed to perceive and understand both texts and images. Starting from the Qwen-LM as a foundation, we endow it with visual capacity by the meticulously designed (i) visual receptor, (ii) input-output interface, (iii) 3-stage training pipeline, and (iv) multilingual multimodal cleaned corpus. Beyond the conventional image description and question-answering, we implement the grounding and text-reading ability of Qwen-VLs by aligning image-caption-box tuples. The resulting models, including Qwen-VL and Qwen-VL-Chat, set new records for generalist models under similar model scales on a broad range of visual-centric benchmarks (e.g., image captioning, question answering, visual grounding) and different settings (e.g., zero-shot, few-shot). Moreover, on real-world dialog benchmarks, our instruction-tuned Qwen-VL-Chat also demonstrates superiority compared to existing vision-language chatbots. Code, demo and models are available at https://github.com/QwenLM/Qwen-VL.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2308.12966")

Code

Syntology Ran 0 of 2 code samples harvested from 1 repository linked to this paper; 2 have no recorded run.

By repository: community (archive-listed): 2 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

qwenlm/qwen-vl officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
brandon3964/multimodal-task-vector mentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

2 samples harvested; 0 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2unverified

Licence: 2 of the 2 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from brandon3964/multimodal-task-vector. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

ModelHelper brandon3964/multimodal-task-vector/MTV/models.py community (archive-listed) unverified licence not identified · pointer only · 5f3088f85e22e05e · report
QwenHelper brandon3964/multimodal-task-vector/MTV/models.py community (archive-listed) unverified licence not identified · pointer only · 01391d17c606d5b6 · report

Tasks

Chart Question AnsweringFS-MEVQAImage CaptioningLanguage ModelingLanguage ModellingMMR totalNatural Language Visual GroundingQuestion AnsweringReferring Expression SegmentationSpatial ReasoningVisual GroundingVisual LocalizationVisual Question AnsweringVisual Question Answering (VQA)

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Chart Question Answering ChartQA Qwen-VL-Chat 1:1 Accuracy 66.3 #17 of 27 Archive leaderboard report
Chart Question Answering ChartQA Qwen-VL 1:1 Accuracy 65.7 #19 of 27 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max #Learning Samples (N) 16 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max ACC 40.33 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max BLEU-4 24.30 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max CIDEr 201.47 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max Detection 1.05 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max METEOR 23.40 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max ROUGE-L 34.52 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max SPICE 26.13 #4 of 7 Archive leaderboard report
MMR total MRR-Benchmark Qwen-vl-max Total Column Score 366 #7 of 14 Archive leaderboard report
MMR total MRR-Benchmark Qwen-vl-plus Total Column Score 310 #9 of 14 Archive leaderboard report
Natural Language Visual Grounding ScreenSpot Qwen-VL Accuracy (%) 5.2 #18 of 18 Archive leaderboard report
Spatial Reasoning EmbSpatial-Bench Qwen-VL-Max Generation 49.11 #2 of 5 Archive leaderboard report
Visual Question Answering MM-Vet Qwen-VL-Max GPT-4 score 66.6±0.5 #17 of 231 Archive leaderboard report
Visual Question Answering MM-Vet Qwen-VL-Plus GPT-4 score 61.1±0.2 #34 of 231 Archive leaderboard report
Visual Question Answering MM-Vet v2 Qwen-VL-Max GPT-4 score 55.8±0.2 #12 of 24 Archive leaderboard report
Visual Question Answering ViP-Bench Qwen-VL-Chat (Coordinates) GPT-4 score (bbox) 45.3 #6 of 13 Archive leaderboard report
Visual Question Answering ViP-Bench Qwen-VL-Chat (Visual Prompt) GPT-4 score (bbox) 39.2 #9 of 13 Archive leaderboard report
Visual Question Answering ViP-Bench Qwen-VL-Chat (Visual Prompt) GPT-4 score (human) 41.7 #9 of 13 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test Qwen-VL-Plus ANLS 0.9024 #5 of 33 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test Qwen-VL ANLS 0.651 #31 of 33 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test Qwen-VL-Chat ANLS 0.626 #33 of 33 Archive leaderboard report
Visual Question Answering (VQA) InfiMM-Eval Qwen-VL-Chat Abductive 44.39 #3 of 14 Archive leaderboard report
Visual Question Answering (VQA) InfiMM-Eval Qwen-VL-Chat Analogical 30.42 #3 of 14 Archive leaderboard report
Visual Question Answering (VQA) InfiMM-Eval Qwen-VL-Chat Deductive 37.55 #3 of 14 Archive leaderboard report
Visual Question Answering (VQA) InfiMM-Eval Qwen-VL-Chat Overall score 37.39 #3 of 14 Archive leaderboard report
Visual Question Answering (VQA) InfiMM-Eval Qwen-VL-Chat Params 16B #3 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections