NarrLV
Models generate videos from prompts that describe changes in a scene, an object, or an action. A multimodal judge checks what appears and in what order.
The project compares nine video generators on fidelity, coverage, and coherence. It reports each measure separately for three kinds of change.
- Made by
- AMAP, Alibaba Group and collaborators
- Released
- May 2025
- Kind
- Video generation
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Image, video and 3D generation
- Last model added
- February 2025
- Scores refreshed
- November 20th, 2026
Wan2.1-T2V-14B leads with 67.1 Wan2.1-T2V-14B leads with 67.1
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Plain mean of nine scores covering three narrative measures and three change factors. 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. This view shows only models we track, each at its best.
- 1
Wan2.1-T2V-14B 67.1
- 2 VGOT 64.2
- 3 SkyReels-V2 61.4
- 4 HunyuanVideo 60.6
- 5 Open-Sora 58.4
- 6 CogVideoX 57.2
- 7 FreeNoise 57.2
- 8 FreeLong 57.0
- 9 MAGI 57.0
- 10 FIFO-Diffusion 55.9
- 11 Open-Sora-Plan 55.1
- 12 FreePCA 54.7
- 13 RIFLEx 52.9
- 14 TALC 30.9
Source: The NarrLV paper
Source: The NarrLV paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 67.1 | Feb 2025 | Official leaderboard | |
| 2 | VGOT | 64.2 | Official leaderboard | ||
| 3 | SkyReels-V2 | 61.4 | Official leaderboard | ||
| 4 | HunyuanVideo | 60.6 | Official leaderboard | ||
| 5 | Open-Sora | 58.4 | Official leaderboard | ||
| 6 | CogVideoX | 57.2 | Official leaderboard | ||
| 7 | FreeNoise | 57.2 | Official leaderboard | ||
| 8 | FreeLong | 57.0 | Official leaderboard | ||
| 9 | MAGI | 57.0 | Official leaderboard | ||
| 10 | FIFO-Diffusion | 55.9 | Official leaderboard | ||
| 11 | Open-Sora-Plan | 55.1 | Official leaderboard | ||
| 12 | FreePCA | 54.7 | Official leaderboard | ||
| 13 | RIFLEx | 52.9 | Official leaderboard | ||
| 14 | TALC | 30.9 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 67.1 | Feb 2025 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official NarrLV 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
- 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 21 months ago, in February 2025, for Wan2.1-T2V-14B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (14 entries).
- Pass Models scored 1 model we track, plus 13 other entries on its leaderboard.
- Warning Newest score The newest came 21 months ago, in February 2025, for Wan2.1-T2V-14B.
- 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 amap-ml.github.io: 1 row for models we track and 13 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.