Benchmark Almanac

EduVideoBench

Not in model cards

Models generate classroom videos intended to teach facts, skills, or attitudes. Experts assess instructional accuracy, presentation, and educational safety.

Released
May 2026
Kind
Video generation
Level
University
Scored
Graded by people
Answers
Open-ended
Tasks
All public
Measures
Capability
Subject
Education
Language
English
In and out
Text → Video
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Scores refreshed
November 20th, 2026
5
Entries on its own leaderboard, 3 models we track

Wan 2.6 leads with 0.59 Wan 2.6 leads with 0.59

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. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

  1. 1 Wan 2.6 VLM-Center 0.59
  2. 2 Sora 2 VLM-Center 0.53
  3. 3 Kling 3.0 VLM-Center 0.42
  4. 4 Veo 3.1 Audio VLM-Center 0.41
  5. 5 Wan 2.2 VLM-Center 0.28

Source: Official EduVideoBench leaderboard

Source: Official EduVideoBench leaderboard

#EntryScoreSettingDateSource
1 Wan 2.6 0.59 VLM-Center Official leaderboard
2 Sora 2 0.53 VLM-Center Official leaderboard
3 Kling 3.0 0.42 VLM-Center Official leaderboard
4 Veo 3.1 Audio 0.41 VLM-Center Official leaderboard
5 Wan 2.2 0.28 VLM-Center Official leaderboard
#ModelScoreSettingDateSource
1 Wan 2.6 0.59 VLM-Center Official leaderboard
2 Sora 2 0.53 VLM-Center Official leaderboard
3 Veo 3.1 Audio 0.41 VLM-Center Official leaderboard

Rankings by part

We read 12 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as K-CK, K-PK and Knowledge. Wan 2.6 leads 10 of them, and Sora 2 leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.

K-CK

3 models we track have a score here.

  1. 1 Wan 2.6 0.56
  2. 2 Sora 2 0.51
  3. 3 Veo 3.1 Audio 0.44

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Wan 2.6
Human-Center VLM-Center
0.59
Sora 2
Human-Center VLM-Center
0.53
Veo 3.1 Audio
Human-Center VLM-Center
0.41

Source: Official EduVideoBench leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Wan 2.6 VLM-Center 0.59
Sora 2 VLM-Center 0.53
Wan 2.6 Human-Center 0.45
Veo 3.1 Audio VLM-Center 0.41
Sora 2 Human-Center 0.38
Veo 3.1 Audio Human-Center 0.25

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Wan 2.6
Human-Center VLM-Center
0.59
Sora 2
Human-Center VLM-Center
0.53
Veo 3.1 Audio
Human-Center VLM-Center
0.41

Source: Official EduVideoBench leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Wan 2.6 VLM-Center 0.59
Sora 2 VLM-Center 0.53
Wan 2.6 Human-Center 0.45
Veo 3.1 Audio VLM-Center 0.41
Sora 2 Human-Center 0.38
Veo 3.1 Audio Human-Center 0.25

Scores over time

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

No dated values yet.

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 (5 entries).
  • Pass Models scored 3 models we track, plus 2 other entries on its leaderboard.
  • Note Newest score No scores yet.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on anonymous.4open.science: 6 rows for models we track and 2 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