Benchmark Almanac

Qwen-Music Cover Song Generation

Qwen-Music (section) 1.44 tops its leaderboard
Not in model cards

Models remake a reference melody using requested lyrics and style. The evaluation aligns the melodies and measures their average pitch difference in semitones.

The Qwen-Music technical report tests 200 generated references and 200 openly licensed references. Suno appears only on the generated set.

Released
July 2026
Kind
Audio understanding and voice
Level
University
Scored
Checked automatically
Answers
Open-ended
Measures
Capability
Subject
Arts
Language
English
In and out
Audio, Text → Audio
Interaction
Single turn
Refresh
One fixed set
Run by
A host
In views
Audio and speech
5
Entries in its paper, 0 models we track

Qwen-Music (section) tops the leaderboard with 1.44

Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. The source reports no overall score, so the headline is the Melody MAE part, which is lower better. 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 Qwen-Music (section) Openly licensed reference melody 1.44
  2. 2 MiniMax Cover Openly licensed reference melody 1.76
  3. 3 Qwen-Music (unique section) AI-generated reference melody 1.80
  4. 4 Suno V5 AI-generated reference melody 1.87
  5. 5 Suno V5.5 AI-generated reference melody 2.00

Source: The Qwen-Music Cover Song Generation paper

#EntryScoreSettingDateSource
1 Qwen-Music (section) 1.44 Openly licensed reference melody Official leaderboard
2 MiniMax Cover 1.76 Openly licensed reference melody Official leaderboard
3 Qwen-Music (unique section) 1.80 AI-generated reference melody Official leaderboard
4 Suno V5 1.87 AI-generated reference melody Official leaderboard
5 Suno V5.5 2.00 AI-generated reference melody 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

7 of 8 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (5 entries).
  • Pass Models scored 5 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 arxiv.org: 5 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.

How we check