Benchmark Almanac

SuperCLUE Arena Reference to Video

Seedance 2.0 [720p] 1,139 tops its leaderboard
Not in model cards

Models generate videos from references. The arena ranks systems from pairwise comparisons.

The arena reports median ratings and uncertainty intervals.

Made by
SuperCLUE
Kind
Video generation
Level
University
Scored
Ranked by matches
Answers
Open-ended
Tasks
All public
Measures
Preference
Language
Chinese
In and out
Images, Text → Video
Interaction
Single turn
Items from
Live play or votes
Refresh
Live
Run by
A host
12
Entries on its own leaderboard, 0 models we track

Seedance 2.0 [720p] tops the leaderboard with 1,139

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.

Bars start at 700.

  1. 1 Seedance 2.0 [720p] 720p 1,139
  2. 2 Veo 3.1 [720p] 720p 1,121
  3. 3 可灵 3.0 Omni [1080p] 1080p 1,116
  4. 4 Vidu Q2 [720p] 720p 1,114
  5. 5 Wan 2.7 [1080p] 1080p 1,081
  6. 6 HappyHorse-1.0 [1080p] 1080p 1,047
  7. 7 可灵 O1(2025-12-15) [1080p] 1080p 1,035
  8. 8 Vidu Q3 [540p] 540p 1,011
  9. 9 可灵 1.6 [1080p] 1080p 885
  10. 10 vivago2.0(智小象AI) [1080p] 1080p 883
  11. 11 PixVerse V5 [540p] 540p 819
  12. 12 Seedance 1.0 lite [1248x704] 1248x704 752

Source: Official SuperCLUE Arena Reference to Video leaderboard

#EntryScore ±SettingDateSource
1 Seedance 2.0 [720p] 1,139 1110.4 to 1169.2 720p Official leaderboard
2 Veo 3.1 [720p] 1,121 ±19.3 720p Official leaderboard
3 可灵 3.0 Omni [1080p] 1,116 ±18.7 1080p Official leaderboard
4 Vidu Q2 [720p] 1,114 1097.4 to 1133.5 720p Official leaderboard
5 Wan 2.7 [1080p] 1,081 1056.2 to 1103.4 1080p Official leaderboard
6 HappyHorse-1.0 [1080p] 1,047 ±25.7 1080p Official leaderboard
7 可灵 O1(2025-12-15) [1080p] 1,035 1014.7 to 1051.1 1080p Official leaderboard
8 Vidu Q3 [540p] 1,011 989.2 to 1034.2 540p Official leaderboard
9 可灵 1.6 [1080p] 885 865.5 to 902.9 1080p Official leaderboard
10 vivago2.0(智小象AI) [1080p] 883 ±17.7 1080p Official leaderboard
11 PixVerse V5 [540p] 819 799.8 to 839.8 540p Official leaderboard
12 Seedance 1.0 lite [1248x704] 752 731.5 to 769.9 1248x704 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 All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (12 entries).
  • Pass Models scored 12 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a rating, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on superclueai.com: 12 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