Benchmark Almanac

ADQA

AutoAD-III 63.5% tops its leaderboard
Not in model cards

Models describe film scenes. An evaluator answers questions from the descriptions and dialogue, then checks whether the context supports each correct answer.

The CoherentAD team submitted its descriptions for scoring. It reports 64.0% correct answers supported by context on narrative understanding.

Released
October 2025
Kind
Video captioning
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Video, Audio → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
A host
5
Entries in its paper, 0 models we track

AutoAD-III tops the leaderboard with 63.5%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

  1. 1 AutoAD-III CMD-AD, narrative understanding 63.5%
  2. 2 AutoAD-Zero CMD-AD, narrative understanding 63.2%
  3. 3 UniAD CMD-AD, narrative understanding 63.2%
  4. 4 NarrAD MAD-eval, narrative understanding 52.4%
  5. 5 Q2VL CMD-AD, narrative understanding 51.5%

Source: The ADQA paper

#EntryScoreSettingDateSource
1 AutoAD-III 63.5% CMD-AD, narrative understanding Official leaderboard
2 AutoAD-Zero 63.2% CMD-AD, narrative understanding Official leaderboard
3 UniAD 63.2% CMD-AD, narrative understanding Official leaderboard
4 NarrAD 52.4% MAD-eval, narrative understanding Official leaderboard
5 Q2VL 51.5% CMD-AD, narrative understanding Official leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Audio and video

All 695 in Audio and video
  • Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
  • LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
  • MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
  • MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
  • FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
  • VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (5 entries).
  • Pass Models scored 5 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on katha-ai.github.io: 5 entries at the last read, none a model we track.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check