MSD-I Multimodal Genre Classification
Models predict a track’s genre from its audio and album cover. The published test contains 4,649 tracks across 15 genres.
A later study reports MSD-I genre results without identifying its test rows. The released training and test sets share 70 cover URLs and no artist IDs.
- Made by
- Universitat Pompeu Fabra and collaborators
- Released
- April 2018
- Kind
- Audio understanding and voice
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Arts
- Interaction
- Single turn
- Items from
- Real work and use, Another benchmark
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- A version of another benchmark
- In views
- Vision, Audio and speech
ALL tops the leaderboard with 0.43
Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. 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 ALL 0.43
- 2 CNN_AUDIO + CNN_VISUAL 0.42
- 3 MM_AUDIO + MM_VISUAL 0.40
- 4 CNN_AUDIO + MM_AUDIO 0.35
- 5 CNN_AUDIO 0.34
- 6 MM_AUDIO 0.33
- 7 CNN_VISUAL 0.26
- 8 CNN_VISUAL + MM_VISUAL 0.24
- 9 MM_VISUAL 0.24
Source: The MSD-I Multimodal Genre Classification paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | ALL | 0.43 | Official leaderboard | ||
| 2 | CNN_AUDIO + CNN_VISUAL | 0.42 | Official leaderboard | ||
| 3 | MM_AUDIO + MM_VISUAL | 0.40 | Official leaderboard | ||
| 4 | CNN_AUDIO + MM_AUDIO | 0.35 | Official leaderboard | ||
| 5 | CNN_AUDIO | 0.34 | Official leaderboard | ||
| 6 | MM_AUDIO | 0.33 | Official leaderboard | ||
| 7 | CNN_VISUAL | 0.26 | Official leaderboard | ||
| 8 | CNN_VISUAL + MM_VISUAL | 0.24 | Official leaderboard | ||
| 9 | MM_VISUAL | 0.24 | 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
- 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 benchmark’s paper (9 entries).
- Pass Models scored 9 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 transactions.ismir.net: 9 entries at the last read, none a model we track.
- Pass Last read November 21st, 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.