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

Video Question Answering

250 papers with code · 28 benchmarks · 43 datasets archive 2025-07-28

Computer VisionReasoning

Benchmarks archive 2025-07-28

28 leaderboard tables shown for this task, 28 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 28 until expanded.

Syntology 7 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; 0 placed): NExT-QA (2 judged, 0 placed), MVBench (5 judged, 0 placed), MSRVTT-QA (1 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
NExT-QA (47 rows) LinVT-Qwen2-VL (7B) LinVT: Empower Your Image-level Large Language Model to Understand Videos code Syntology official (archive's flag): 7 ran · 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified Compare
ActivityNet-QA (36 rows) GPT-2 + CLIP-14 + CLIP-multilingual (Zero-Shot) Composing Ensembles of Pre-trained Models via Iterative Consensus — — Compare
TVBench (28 rows) Seed1.5-VL thinking Seed1.5-VL Technical Report — — Compare
MVBench (22 rows) LinVT-Qwen2-VL (7B) LinVT: Empower Your Image-level Large Language Model to Understand Videos code Syntology official (archive's flag): 7 ran · 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified Compare
STAR Benchmark (17 rows) VLAP (4 frames) ViLA: Efficient Video-Language Alignment for Video Question Answering code Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 0 unverified Compare
OVBench (16 rows) Seed1.5-VL Seed1.5-VL Technical Report — — Compare
MSRVTT-QA (14 rows) Mirasol3B Mirasol3B: A Multimodal Autoregressive model for time-aligned and... — — Compare
AGQA 2.0 balanced (8 rows) GF (sup) - Faster RCNN Glance and Focus: Memory Prompting for Multi-Event Video Question Answering code Syntology official (archive's flag): 14 ran · 14 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified Compare
How2QA (8 rows) Text + Text (no Multimodal Pretext Training) Towards Fast Adaptation of Pretrained Contrastive Models for... 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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
iVQA (7 rows) Text + Text (no Multimodal Pretext Training) Towards Fast Adaptation of Pretrained Contrastive Models for... 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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
MSRVTT-MC (7 rows) VIOLETv2 An Empirical Study of End-to-End Video-Language Transformers with... code — Compare
IntentQA (6 rows) VideoChat2_HD_mistral MVBench: A Comprehensive Multi-modal Video Understanding Benchmark code Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified Compare
Perception Test (6 rows) Oyrx (34B) Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
SUTD-TrafficQA (6 rows) CFMMC-Align — — — Compare
TVQA (6 rows) LLaMA-VQA Large Language Models are Temporal and Causal Reasoners for Video... code Syntology official: harvested, nothing ran · 0 ran · 4 unverified Compare
WildQA (5 rows) Multi (text + video, IO) WildQA: In-the-Wild Video Question Answering — — Compare
LSMDC-MC (2 rows) VIOLETv2 An Empirical Study of End-to-End Video-Language Transformers with... code — Compare
NExT-QA (Efficient) (2 rows) ViLA (3B, 4 frames) ViLA: Efficient Video-Language Alignment for Video Question Answering code Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 0 unverified Compare
RoadTextVQA (2 rows) GIT Reading Between the Lanes: Text VideoQA on the Road code — Compare
DramaQA (1 row) LLaMA-VQA Large Language Models are Temporal and Causal Reasoners for Video... code Syntology official: harvested, nothing ran · 0 ran · 4 unverified Compare
Howto100M-QA (1 row) TimeSformer Is Space-Time Attention All You Need for Video Understanding? code Syntology official: no sample here; runs from other or unrecorded repositories · 35 ran (of which 17 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 14 where Syntology's instrument failed) · 8 unverified Compare
LSMDC-FiB (1 row) Clover Clover: Towards A Unified Video-Language Alignment and Fusion Model code — Compare
MSR-VTT (1 row) LocVLM-Vid-B Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs code — Compare
MSR-VTT-MC (1 row) ATP (1<-16) Revisiting the "Video" in Video-Language Understanding code Syntology 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
MSVD-QA (1 row) LocVLM-Vid-B Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs code — Compare
TGIF-QA (1 row) LocVLM-Vid-B Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs code — Compare
VideoQA (1 row) Just Ask (fine-tune) Just Ask: Learning to Answer Questions from Millions of Narrated Videos code — Compare
VLEP (1 row) LLaMA-VQA Large Language Models are Temporal and Causal Reasoners for Video... code Syntology official: harvested, nothing ran · 0 ran · 4 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

43 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 43 until expanded.

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 460 · with a code link: 250 · where Syntology ran a sample: 124 (104 with a run with no instrument failure, 20 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (124 of 460 tagged: 104 with a run with no instrument failure, 20 where every run was a failure of Syntology's instrument)

Page 1 of 5: papers 1 to 100 of 460, 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 61 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