Benchmark Almanac

AV-SafetyBench

JavisDiT++ 25.1% tops its leaderboard LTX-2.3 49.4% leads the models we track
Not in model cards

Models generate videos with sound from written prompts. Judges review each clip with sound, in silence, and as audio alone to identify unsafe outputs.

Released
September 2026
Kind
Video generation
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Measures
Propensity
Behavior
Harmful use
Language
English
In and out
Text → Video, Audio
Interaction
Single turn
Refresh
One fixed set
Run by
A host
Last model added
March 2026
Scores refreshed
November 20th, 2026
5
Entries on its own leaderboard, 1 model we track

JavisDiT++ tops the leaderboard with 25.1% LTX-2.3 leads with 49.4%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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. The best model we track is LTX-2.3, at 49.4%. This view shows only models we track, each at its best.

  1. 1 JavisDiT++ Gemini judgments 25.1%
  2. 2 NAVA Gemini judgments 39.1%
  3. 3 Ovi-1.1 Gemini judgments 45.8%
  4. 4 daVinci Gemini judgments 46.7%
  5. 5 LTX-2.3 Gemini judgments 49.4%

Source: Official AV-SafetyBench leaderboard

Source: Official AV-SafetyBench leaderboard

#EntryScoreSettingDateSource
1 JavisDiT++ 25.1% Gemini judgments Official leaderboard
2 NAVA 39.1% Gemini judgments Official leaderboard
3 Ovi-1.1 45.8% Gemini judgments Official leaderboard
4 daVinci 46.7% Gemini judgments Official leaderboard
5 LTX-2.3 49.4% Gemini judgments Mar 2026 Official leaderboard
#ModelScoreSettingDateSource
1 LTX-2.3 49.4% Gemini judgments Mar 2026 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 LTX-2.3 0% 20% 40% 60% 80% 100% 2026 LTX-2.3

Source: Official AV-SafetyBench 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

7 of 9 checks pass, 2 warnings. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (5 entries).
  • Pass Models scored 1 model we track, plus 4 other entries on its leaderboard.
  • Warning Newest score The newest came 8 months ago, in March 2026, for LTX-2.3.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
  • Pass Importer We read the board on miko-mitama.github.io: 2 rows for models we track and 4 other entries at the last read.
  • 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