Benchmark Almanac

SuperCLUE Arena Text to Video

Seedance 2.5 [720p] 1,263 tops its leaderboard
Not in model cards

Models generate videos from text. 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
In and out
Text → Video
Interaction
Single turn
Items from
Live play or votes
Refresh
Live
Run by
A host
25
Entries on its own leaderboard, 0 models we track

Seedance 2.5 [720p] tops the leaderboard with 1,263

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 400.

  1. 1 Seedance 2.5 [720p] 720p 1,263
  2. 2 Seedance 2.0 [720p] 720p 1,257
  3. 3 MiniMax H3 [768p] 768p 1,220
  4. 4 可灵 3.0 [720p] 720p 1,192
  5. 5 Veo 3.1 [720p] 720p 1,177
  6. 6 Wan 2.7 [1080p] 1080p 1,148
  7. 7 HappyHorse-1.0 [720p] 720p 1,105
  8. 8 veo-3.0-generate-preview [720p] 720p 1,089
  9. 9 PixVerse V6 [720p] 720p 1,077
  10. 10 Luma Ray 3 [1080p] 1080p 1,053
  11. 11 Vidu Q3 [1080p] 1080p 1,040
  12. 12 Hailuo-02 [1080p] 1080p 1,032
  13. 13 可灵 2.5 Turbo [1080p] 1080p 1,027
  14. 14 可灵 O1(2025-12-01) [1080p] 1080p 1,001
  15. 15 Wan 2.6(2025-12-16) [1080p] 1080p 995
  16. 16 Hailuo-2.3 [1080p] 1080p 984
  17. 17 可灵 2.1 大师版 [1080p] 1080p 978
  18. 18 Wan 2.5 Preview [1080p] 1080p 972
  19. 19 Seedance 1.5 Pro [720p] 720p 943
  20. 20 PixVerse V5 [1080p] 1080p 915
  21. 21 PixVerse V5.5 [1080p] 1080p 897
  22. 22 Wan2.1-T2V-14B [720p] 720p 795
  23. 23 pika 2.2 [1080p] 1080p 726
  24. 24 Hunyuan Video [720p] 720p 628
  25. 25 Open-Sora-v2 [576p] 576p 487

Source: Official SuperCLUE Arena Text to Video leaderboard

#EntryScore ±SettingDateSource
1 Seedance 2.5 [720p] 1,263 ±43.4 720p Official leaderboard
2 Seedance 2.0 [720p] 1,257 1236 to 1277.3 720p Official leaderboard
3 MiniMax H3 [768p] 1,220 ±41.6 768p Official leaderboard
4 可灵 3.0 [720p] 1,192 1169.6 to 1212.2 720p Official leaderboard
5 Veo 3.1 [720p] 1,177 1152 to 1201 720p Official leaderboard
6 Wan 2.7 [1080p] 1,148 ±20.3 1080p Official leaderboard
7 HappyHorse-1.0 [720p] 1,105 1086 to 1125.8 720p Official leaderboard
8 veo-3.0-generate-preview [720p] 1,089 1071 to 1108.4 720p Official leaderboard
9 PixVerse V6 [720p] 1,077 1056.7 to 1096.8 720p Official leaderboard
10 Luma Ray 3 [1080p] 1,053 1030.8 to 1077.6 1080p Official leaderboard
11 Vidu Q3 [1080p] 1,040 1018.4 to 1060.3 1080p Official leaderboard
12 Hailuo-02 [1080p] 1,032 ±20.9 1080p Official leaderboard
13 可灵 2.5 Turbo [1080p] 1,027 ±23.8 1080p Official leaderboard
14 可灵 O1(2025-12-01) [1080p] 1,001 ±23.3 1080p Official leaderboard
15 Wan 2.6(2025-12-16) [1080p] 995 ±18.9 1080p Official leaderboard
16 Hailuo-2.3 [1080p] 984 ±22.4 1080p Official leaderboard
17 可灵 2.1 大师版 [1080p] 978 957.6 to 999.8 1080p Official leaderboard
18 Wan 2.5 Preview [1080p] 972 ±23.2 1080p Official leaderboard
19 Seedance 1.5 Pro [720p] 943 ±22.2 720p Official leaderboard
20 PixVerse V5 [1080p] 915 891.3 to 939.7 1080p Official leaderboard
21 PixVerse V5.5 [1080p] 897 ±24.6 1080p Official leaderboard
22 Wan2.1-T2V-14B [720p] 795 774.3 to 813.7 720p Official leaderboard
23 pika 2.2 [1080p] 726 ±20.7 1080p Official leaderboard
24 Hunyuan Video [720p] 628 605.9 to 650.9 720p Official leaderboard
25 Open-Sora-v2 [576p] 487 464.2 to 508.3 576p 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 (25 entries).
  • Pass Models scored 25 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: 25 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