SongBench
Models generate songs from lyrics and a style prompt. A trained music judge scores seven aspects, including the melody, arrangement, vocals, and mix.
The Qwen-Music report uses SongBench to score six generators on its own prompts. The SongBench authors compare 11 generators in their paper.
- Made by
- Tencent and Tsinghua University
- Released
- March 2026
- Kind
- Audio understanding and voice
- Level
- University
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Arts
- Interaction
- Single turn
- Items from
- Generated, Written by experts
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Audio and speech
Mureka V8 tops the leaderboard with 6.87
Best score per entry from the benchmark's paper, read on November 20th, 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 Mureka V8 6.87
- 2 Suno v5 6.86
- 3 Suno v4.5+ 6.79
- 4 Mureka O2 6.67
- 5 Suno v4.5 6.60
- 6 MiniMax 2.5 6.52
- 7 MiniMax 2.0 6.37
- 8 ACE-Step v1.5 6.04
- 9 HeartMuLa 5.80
- 10 LeVo 5.18
- 11 Diffrhythm 2 4.93
Source: The SongBench paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Mureka V8 | 6.87 | Official leaderboard | ||
| 2 | Suno v5 | 6.86 | Official leaderboard | ||
| 3 | Suno v4.5+ | 6.79 | Official leaderboard | ||
| 4 | Mureka O2 | 6.67 | Official leaderboard | ||
| 5 | Suno v4.5 | 6.60 | Official leaderboard | ||
| 6 | MiniMax 2.5 | 6.52 | Official leaderboard | ||
| 7 | MiniMax 2.0 | 6.37 | Official leaderboard | ||
| 8 | ACE-Step v1.5 | 6.04 | Official leaderboard | ||
| 9 | HeartMuLa | 5.80 | Official leaderboard | ||
| 10 | LeVo | 5.18 | Official leaderboard | ||
| 11 | Diffrhythm 2 | 4.93 | 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 (11 entries).
- Pass Models scored 11 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 github.com: 11 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.