Benchmark Almanac

ChronoMagic-Bench

MagicTime 0.48 tops its leaderboard
Not in model cards

Video models generate time-lapse scenes from 1,649 prompts covering biological, human-made, weather, and physical changes. Automatic metrics measure the amount of change and temporal coherence, with a separate GPT-4o assessment of change.

The separate ChronoMagic-Pro collection is training data. The makers changed the temporal-coherence metric in September 2024, so metric versions must accompany comparisons.

Released
June 2024
Announced on X
2.6K views, 34 likes
Kind
Video generation
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Video
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone

In the authors’ words

We propose a novel text-to-video (T2V) generation benchmark, ChronoMagic-Bench, to evaluate the temporal and metamorphic capabilities of the T2V models (e.g. Sora and Lumiere) in time-lapse video generation. In contrast to existing benchmarks that focus on visual quality and textual relevance of generated videos, ChronoMagic-Bench focuses on the model's ability to generate time-lapse videos with significant metamorphic amplitude and temporal coherence. The benchmark probes T2V models for their physics, biology, and chemistry capabilities, in a free-form text query. For these purposes, ChronoMagic-Bench introduces 1,649 prompts and real-world videos as references, categorized into four major types of time-lapse videos: biological, human-created, meteorological, and physical phenomena, which are further divided into 75 subcategories. This categorization comprehensively evaluates the model's capacity to handle diverse and complex transformations. To accurately align human preference with the benchmark, we introduce two new automatic metrics, MTScore and CHScore, to evaluate the videos' metamorphic attributes and temporal coherence. MTScore measures the metamorphic amplitude, reflecting the degree of change over time, while CHScore assesses the temporal coherence, ensuring the generated videos maintain logical progression and continuity. Based on ChronoMagic-Bench, we conduct comprehensive manual evaluations of ten representative T2V models, revealing their strengths and weaknesses across different categories of prompts, and providing a thorough evaluation framework that addresses current gaps in video generation research. Moreover, we create a large-scale ChronoMagic-Pro dataset, containing 460k high-quality pairs of 720p time-lapse videos and detailed captions ensuring high physical pertinence and large metamorphic amplitude. [Homepage](https://pku-yuangroup.github.io/ChronoMagic-Bench/).

Abstract of ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation (arXiv:2406.18522, CC0)
14
Entries on its own leaderboard, 0 models we track

MagicTime tops the leaderboard with 0.48

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.

  1. 1 MagicTime 0.48
  2. 2 AnimateDiff-V3 0.47
  3. 3 OpenSora 1.1 0.44
  4. 4 VideoCrafter2 0.43
  5. 5 MCM-MSLION 0.42
  6. 6 CogVideoX-2B 0.40
  7. 7 ModelScopeT2V 0.40
  8. 8 T2V-Zero 0.40
  9. 9 ZeroScope 0.40
  10. 10 OpenSora 1.2 0.38
  11. 11 Latte 0.36
  12. 12 EasyAnimate V3 0.35
  13. 13 LaVie 0.35
  14. 14 OpenSoraPlan v1.1 0.33

Source: Official ChronoMagic-Bench leaderboard

#EntryScoreSettingDateLinkSource
1 MagicTime 0.48 github.com Official leaderboard
2 AnimateDiff-V3 0.47 github.com Official leaderboard
3 OpenSora 1.1 0.44 github.com Official leaderboard
4 VideoCrafter2 0.43 github.com Official leaderboard
5 MCM-MSLION 0.42 yhzhai.github.io Official leaderboard
6 CogVideoX-2B 0.40 github.com Official leaderboard
7 ModelScopeT2V 0.40 huggingface.co Official leaderboard
8 T2V-Zero 0.40 github.com Official leaderboard
9 ZeroScope 0.40 huggingface.co Official leaderboard
10 OpenSora 1.2 0.38 github.com Official leaderboard
11 Latte 0.36 github.com Official leaderboard
12 EasyAnimate V3 0.35 github.com Official leaderboard
13 LaVie 0.35 github.com Official leaderboard
14 OpenSoraPlan v1.1 0.33 github.com 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 (14 entries).
  • Pass Models scored 14 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 plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 14 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