Browse State-of-the-Art › Visual Question Answering

Visual Question Answering

1,042 papers with code · 29 benchmarks · 32 datasets archive 2025-07-28

Computer VisionNatural Language Processing

MLLM Leaderboard

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

29 leaderboard tables shown for this task, 29 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 29 until expanded.

Syntology 30 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): MM-Vet (3 judged, 0 placed), MMBench (8 judged, 0 placed), V*bench (4 judged, 0 placed), VQA v2 test-std (1 judged, 0 placed), MMHal-Bench (1 judged, 0 placed), AMBER (2 judged, 1 placed), CLEVR (3 judged, 0 placed), GQA (7 judged, 0 placed), TextVQA test-standard (4 judged, 0 placed), VizWiz (5 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
MM-Vet (231 rows) gemini-2.0-flash-exp — — — Compare
MM-Vet v2 (24 rows) gemini-2.0-flash-exp — — — Compare
ViP-Bench (13 rows) GPT-4V-turbo-detail:high (Visual Prompt) GPT-4 Technical Report code Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
VQA v2 test-dev (11 rows) BLIP-2 ViT-G OPT 6.7B (fine-tuned) BLIP-2: Bootstrapping Language-Image Pre-training with Frozen... code Syntology community repositories only · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result Compare
BenchLMM (10 rows) GPT-4V GPT-4 Technical Report code Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
MMBench (5 rows) LLaVA-InternLM2-ViT + MoSLoRA Mixture-of-Subspaces in Low-Rank Adaptation code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
V*bench (5 rows) LLaVA-OneVision7B w. FOCUS FOCUS: Internal MLLM Representations for Efficient Fine-Grained... — — Compare
MSRVTT-QA (4 rows) Aurora (ours, r=64) Aurora (ours, r=64) — — — Compare
VQA v2 val (4 rows) BLIP-2 ViT-G OPT 6.7B (fine-tuned) BLIP-2: Bootstrapping Language-Image Pre-training with Frozen... code Syntology community repositories only · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result Compare
VQA v2 test-std (3 rows) LXMERT (low-magnitude pruning) LXMERT Model Compression for Visual Question Answering code — Compare
MMHal-Bench (2 rows) RLAIF-V 12B RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness code Syntology official (archive's flag): 11 ran · 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 3 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified Compare
MSVD-QA (2 rows) FrozenBiLM Zero-Shot Video Question Answering via Frozen Bidirectional Language Models code Syntology official: harvested, nothing ran · 14 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 20 unverified Compare
PlotQA-D1 (2 rows) MatCha4096 + LaMenDa Synthesize Step-by-Step: Tools Templates and LLMs as Data... — — Compare
PlotQA-D2 (2 rows) MatCha4096 + LaMenDa Synthesize Step-by-Step: Tools Templates and LLMs as Data... — — Compare
VQA v2 (2 rows) RLHF-V RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from... code — Compare
AID-VQA (1 row) SkySense-O SkySense: A Multi-Modal Remote Sensing Foundation Model Towards... code — Compare
AMBER (1 row) RLAIF-V 12B RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness code Syntology official (archive's flag): 11 ran · 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 3 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified Compare
CLEVR (1 row) NeSyCoCo Neuro-Symbolic NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional... code — Compare
COCO Visual Question Answering (VQA) real images 2.0 open ended (1 row) MaMMUT (2B) MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks code Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
EarthVQA (1 row) SOBA EarthVQA: Towards Queryable Earth via Relational Reasoning-Based... code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified Compare
GQA (1 row) LocVLM-L Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs code — Compare
GRIT (1 row) OFA OFA: Unifying Architectures, Tasks, and Modalities Through a... code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
MapEval-Visual (1 row) Claude-3.5-Sonnet MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in... code Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified Compare
MM-Vet (w/o External Tools) (1 row) Emu-14B Emu: Generative Pretraining in Multimodality code Syntology official: harvested for another paper · 0 ran · 2 unverified Compare
RSVQA-HR (1 row) SkySense-O SkySense: A Multi-Modal Remote Sensing Foundation Model Towards... code — Compare
SIRI-WHU (1 row) SkySense-O SkySense: A Multi-Modal Remote Sensing Foundation Model Towards... code — Compare
TextVQA test-standard (1 row) PromptCap PromptCap: Prompt-Guided Task-Aware Image Captioning code — Compare
VisualMRC (1 row) LayoutT5 (Large) VisualMRC: Machine Reading Comprehension on Document Images code — Compare
VizWiz (1 row) Emu-I * Emu: Generative Pretraining in Multimodality code Syntology official: harvested for another paper · 0 ran · 2 unverified Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

32 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 32 until expanded.

Subtasks archive 2025-07-28

5 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 2,177 · with a code link: 1,042 · where Syntology ran a sample: 378 (292 with a run with no instrument failure, 86 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (378 of 2,177 tagged: 292 with a run with no instrument failure, 86 where every run was a failure of Syntology's instrument)

Page 1 of 22: papers 1 to 100 of 2,177, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 60 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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