Files
YuE/docs/frontier-composites.json
Ruibin Yuan 88da114a67 Sync Suno v6 WildSongBench results and frontier figure
Add Suno v6 and Suno v6 Wild to the WildSongBench comparison and use the author-approved wording **competitive with Suno v5/v6**. The README now covers 17 settings; the detailed table and CSV/JSON provide all nine reported metrics. Figure 1 and its normalization data match the updated demo and paper.

Validated all 153 aggregate values against the frozen September 12 results, confirmed the previous 15 settings are unchanged, independently checked the plotted coordinates and Pareto set, and verified image-pixel and PDF/SVG parity with the demo. Inference code, checkpoints, listening examples, and cover/editing results are unchanged.
2026-09-12 01:37:59 +08:00

640 lines
16 KiB
JSON
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"dataset": "WSB",
"n_prompts": 192,
"source_sha256": "579ffb6b9b069f6d3cdd32a76788998ec633a12426a0ebb7c9f83e6fb0d5b1fc",
"reference_systems": [
"Suno v5",
"Suno v4.5",
"Suno v5.5",
"Suno v6",
"Suno v6 Wild",
"MiniMax Music 2.6",
"Mureka 9",
"YuE 1",
"SongBloom",
"LeVo 2",
"ACE-Step 1.5",
"HeartMuLa",
"DiffRhythm 2",
"Muse",
"MiniMax Music 3"
],
"normalization": "z = (system mean - reference mean) / reference population std",
"reference_statistics": {
"songbench_global_avg": {
"mean": 6.121283377976191,
"population_std": 0.7357457614725659
},
"songeval_global_avg": {
"mean": 4.015471256944445,
"population_std": 0.40701956006795303
},
"songbench_musicality": {
"mean": 5.265866701388889,
"population_std": 0.7053243399537521
},
"songeval_musicality": {
"mean": 3.9703476041666663,
"population_std": 0.4051162346821886
},
"mulan": {
"mean": 0.4186944833891175,
"population_std": 0.08094623772340859
},
"allmusiccaps": {
"mean": 0.3533851072454733,
"population_std": 0.06820180734302435
},
"control_overall": {
"mean": 4.248089863722948,
"population_std": 0.4756164261685128
}
},
"quality_weights": {
"songbench": 0.6666666666666666,
"songeval": 0.33333333333333337
},
"alignment_weights": {
"mulan": 0.3333333333333333,
"allmusiccaps": 0.3333333333333333,
"control_overall": 0.3333333333333333
},
"values": {
"YuE2": {
"quality_global_avg": 0.7552819777715396,
"quality_musicality": 0.8078339775660601,
"alignment": 0.9210758825216073,
"audiobox_pq": 8.25979095697403
},
"YuE2 (best-of-8)": {
"quality_global_avg": 0.9926775311951548,
"quality_musicality": 1.1764900036325572,
"alignment": 0.8913402282808791,
"audiobox_pq": 8.271365446348986
},
"ACE-Step 1.5": {
"quality_global_avg": -0.2376035047550664,
"quality_musicality": -0.23714600301672967,
"alignment": 0.47315715541685155,
"audiobox_pq": 8.051833018660545
},
"DiffRhythm 2": {
"quality_global_avg": -1.1980739812149017,
"quality_musicality": -1.1559112521857333,
"alignment": -0.41604199452568785,
"audiobox_pq": 7.978225273390611
},
"HeartMuLa": {
"quality_global_avg": 0.5544151508643054,
"quality_musicality": 0.6806476331364909,
"alignment": -1.0459382238546173,
"audiobox_pq": 8.293305036922296
},
"LeVo 2": {
"quality_global_avg": 0.19076064388585245,
"quality_musicality": 0.19203107542441739,
"alignment": -0.8946697129809009,
"audiobox_pq": 8.396623315910498
},
"MiniMax Music 2.6": {
"quality_global_avg": 0.24999255629041012,
"quality_musicality": 0.2385294260172236,
"alignment": 0.317708040770442,
"audiobox_pq": 8.171058195332686
},
"MiniMax Music 3": {
"quality_global_avg": 0.21521779684943682,
"quality_musicality": 0.13768736380561403,
"alignment": 0.06167958802908772,
"audiobox_pq": 8.28245102117459
},
"Mureka 9": {
"quality_global_avg": 1.063838458020569,
"quality_musicality": 1.0622475778213865,
"alignment": 0.6353722959962361,
"audiobox_pq": 8.022609589000544
},
"Muse": {
"quality_global_avg": -0.2640126435903063,
"quality_musicality": -0.28400814299371513,
"alignment": -0.027277572405822206,
"audiobox_pq": 8.051745663086573
},
"SongBloom": {
"quality_global_avg": -2.3727929454241776,
"quality_musicality": -2.3469029518895956,
"alignment": -2.25355622224482,
"audiobox_pq": 8.153916046023369
},
"Suno v4.5": {
"quality_global_avg": 0.8114848653568392,
"quality_musicality": 0.822345947368047,
"alignment": 0.6266794053102317,
"audiobox_pq": 8.254062737027803
},
"Suno v5": {
"quality_global_avg": 0.9607654088358881,
"quality_musicality": 0.9616318815497118,
"alignment": 1.1513277335650094,
"audiobox_pq": 8.169838989774385
},
"Suno v5.5": {
"quality_global_avg": 0.7014955760788759,
"quality_musicality": 0.6606381030854666,
"alignment": 0.7992264544775121,
"audiobox_pq": 8.195489337046942
},
"Suno v6": {
"quality_global_avg": 0.6341407893639396,
"quality_musicality": 0.6097852138267854,
"alignment": 0.9417981546473502,
"audiobox_pq": 8.129587392012278
},
"Suno v6 Wild": {
"quality_global_avg": 0.43765333454931554,
"quality_musicality": 0.44783537273294216,
"alignment": 0.9563182017109547,
"audiobox_pq": 8.178526304662228
},
"YuE 1": {
"quality_global_avg": -1.7472815051109758,
"quality_musicality": -1.7894112446823107,
"alignment": -1.3257833039118254,
"audiobox_pq": 7.868339642882347
}
},
"sensitivity": [
{
"variant": "global_avg",
"songbench_weight": 0.5,
"best_public": "HeartMuLa",
"yue2_minus_best_public": -0.02710930368588904,
"rank_yue2": 6,
"rank_bo8": 3,
"ranking": [
"Mureka 9",
"Suno v5",
"YuE2 (best-of-8)",
"Suno v4.5",
"HeartMuLa",
"YuE2",
"Suno v6",
"Suno v5.5",
"Suno v6 Wild",
"MiniMax Music 2.6",
"MiniMax Music 3",
"LeVo 2",
"ACE-Step 1.5",
"Muse",
"DiffRhythm 2",
"YuE 1",
"SongBloom"
]
},
{
"variant": "global_avg",
"songbench_weight": 0.6,
"best_public": "HeartMuLa",
"yue2_minus_best_public": 0.10967637466998481,
"rank_yue2": 5,
"rank_bo8": 2,
"ranking": [
"Mureka 9",
"YuE2 (best-of-8)",
"Suno v5",
"Suno v4.5",
"YuE2",
"Suno v5.5",
"Suno v6",
"HeartMuLa",
"Suno v6 Wild",
"MiniMax Music 2.6",
"MiniMax Music 3",
"LeVo 2",
"ACE-Step 1.5",
"Muse",
"DiffRhythm 2",
"YuE 1",
"SongBloom"
]
},
{
"variant": "global_avg",
"songbench_weight": 0.6666666666666666,
"best_public": "HeartMuLa",
"yue2_minus_best_public": 0.20086682690723423,
"rank_yue2": 5,
"rank_bo8": 2,
"ranking": [
"Mureka 9",
"YuE2 (best-of-8)",
"Suno v5",
"Suno v4.5",
"YuE2",
"Suno v5.5",
"Suno v6",
"HeartMuLa",
"Suno v6 Wild",
"MiniMax Music 2.6",
"MiniMax Music 3",
"LeVo 2",
"ACE-Step 1.5",
"Muse",
"DiffRhythm 2",
"YuE 1",
"SongBloom"
]
},
{
"variant": "global_avg",
"songbench_weight": 0.7,
"best_public": "HeartMuLa",
"yue2_minus_best_public": 0.24646205302585877,
"rank_yue2": 5,
"rank_bo8": 2,
"ranking": [
"Mureka 9",
"YuE2 (best-of-8)",
"Suno v5",
"Suno v4.5",
"YuE2",
"Suno v5.5",
"Suno v6",
"HeartMuLa",
"Suno v6 Wild",
"MiniMax Music 2.6",
"MiniMax Music 3",
"LeVo 2",
"ACE-Step 1.5",
"Muse",
"DiffRhythm 2",
"YuE 1",
"SongBloom"
]
},
{
"variant": "global_avg",
"songbench_weight": 0.75,
"best_public": "HeartMuLa",
"yue2_minus_best_public": 0.3148548922037958,
"rank_yue2": 5,
"rank_bo8": 2,
"ranking": [
"Mureka 9",
"YuE2 (best-of-8)",
"Suno v5",
"Suno v4.5",
"YuE2",
"Suno v5.5",
"Suno v6",
"HeartMuLa",
"Suno v6 Wild",
"MiniMax Music 2.6",
"MiniMax Music 3",
"LeVo 2",
"ACE-Step 1.5",
"Muse",
"DiffRhythm 2",
"YuE 1",
"SongBloom"
]
},
{
"variant": "global_avg",
"songbench_weight": 0.8,
"best_public": "HeartMuLa",
"yue2_minus_best_public": 0.3832477313817329,
"rank_yue2": 5,
"rank_bo8": 2,
"ranking": [
"Mureka 9",
"YuE2 (best-of-8)",
"Suno v5",
"Suno v4.5",
"YuE2",
"Suno v5.5",
"Suno v6",
"Suno v6 Wild",
"HeartMuLa",
"MiniMax Music 2.6",
"LeVo 2",
"MiniMax Music 3",
"ACE-Step 1.5",
"Muse",
"DiffRhythm 2",
"YuE 1",
"SongBloom"
]
},
{
"variant": "musicality",
"songbench_weight": 0.5,
"best_public": "HeartMuLa",
"yue2_minus_best_public": -0.10071426090411806,
"rank_yue2": 6,
"rank_bo8": 1,
"ranking": [
"YuE2 (best-of-8)",
"Mureka 9",
"Suno v5",
"HeartMuLa",
"Suno v4.5",
"YuE2",
"Suno v6",
"Suno v5.5",
"Suno v6 Wild",
"MiniMax Music 2.6",
"LeVo 2",
"MiniMax Music 3",
"ACE-Step 1.5",
"Muse",
"DiffRhythm 2",
"YuE 1",
"SongBloom"
]
},
{
"variant": "musicality",
"songbench_weight": 0.6,
"best_public": "HeartMuLa",
"yue2_minus_best_public": 0.036026102296094376,
"rank_yue2": 5,
"rank_bo8": 1,
"ranking": [
"YuE2 (best-of-8)",
"Mureka 9",
"Suno v5",
"Suno v4.5",
"YuE2",
"HeartMuLa",
"Suno v5.5",
"Suno v6",
"Suno v6 Wild",
"MiniMax Music 2.6",
"LeVo 2",
"MiniMax Music 3",
"ACE-Step 1.5",
"Muse",
"DiffRhythm 2",
"YuE 1",
"SongBloom"
]
},
{
"variant": "musicality",
"songbench_weight": 0.6666666666666666,
"best_public": "HeartMuLa",
"yue2_minus_best_public": 0.12718634442956922,
"rank_yue2": 5,
"rank_bo8": 1,
"ranking": [
"YuE2 (best-of-8)",
"Mureka 9",
"Suno v5",
"Suno v4.5",
"YuE2",
"HeartMuLa",
"Suno v5.5",
"Suno v6",
"Suno v6 Wild",
"MiniMax Music 2.6",
"LeVo 2",
"MiniMax Music 3",
"ACE-Step 1.5",
"Muse",
"DiffRhythm 2",
"YuE 1",
"SongBloom"
]
},
{
"variant": "musicality",
"songbench_weight": 0.7,
"best_public": "HeartMuLa",
"yue2_minus_best_public": 0.1727664654963067,
"rank_yue2": 5,
"rank_bo8": 1,
"ranking": [
"YuE2 (best-of-8)",
"Mureka 9",
"Suno v5",
"Suno v4.5",
"YuE2",
"Suno v5.5",
"HeartMuLa",
"Suno v6",
"Suno v6 Wild",
"MiniMax Music 2.6",
"LeVo 2",
"MiniMax Music 3",
"ACE-Step 1.5",
"Muse",
"DiffRhythm 2",
"YuE 1",
"SongBloom"
]
},
{
"variant": "musicality",
"songbench_weight": 0.75,
"best_public": "HeartMuLa",
"yue2_minus_best_public": 0.24113664709641314,
"rank_yue2": 4,
"rank_bo8": 1,
"ranking": [
"YuE2 (best-of-8)",
"Mureka 9",
"Suno v5",
"YuE2",
"Suno v4.5",
"Suno v5.5",
"Suno v6",
"HeartMuLa",
"Suno v6 Wild",
"MiniMax Music 2.6",
"LeVo 2",
"MiniMax Music 3",
"ACE-Step 1.5",
"Muse",
"DiffRhythm 2",
"YuE 1",
"SongBloom"
]
},
{
"variant": "musicality",
"songbench_weight": 0.8,
"best_public": "HeartMuLa",
"yue2_minus_best_public": 0.30950682869651935,
"rank_yue2": 4,
"rank_bo8": 1,
"ranking": [
"YuE2 (best-of-8)",
"Mureka 9",
"Suno v5",
"YuE2",
"Suno v4.5",
"Suno v5.5",
"Suno v6",
"HeartMuLa",
"Suno v6 Wild",
"MiniMax Music 2.6",
"LeVo 2",
"MiniMax Music 3",
"ACE-Step 1.5",
"Muse",
"DiffRhythm 2",
"YuE 1",
"SongBloom"
]
}
],
"display_normalization": {
"formula": "index = 10 + 80 * (composite - min) / (max - min)",
"display_range": [
10,
90
],
"axis_range": [
0,
100
],
"endpoint_systems": [
"YuE2",
"YuE2 (best-of-8)",
"ACE-Step 1.5",
"DiffRhythm 2",
"HeartMuLa",
"LeVo 2",
"MiniMax Music 2.6",
"MiniMax Music 3",
"Mureka 9",
"Muse",
"SongBloom",
"Suno v4.5",
"Suno v5",
"Suno v5.5",
"Suno v6",
"Suno v6 Wild",
"YuE 1"
],
"bounds": {
"quality_global_avg": {
"min": -2.3727929454241776,
"max": 1.063838458020569
},
"quality_musicality": {
"min": -2.3469029518895956,
"max": 1.1764900036325572
},
"alignment": {
"min": -2.25355622224482,
"max": 1.1513277335650094
}
},
"scope": "Observed extrema across the frozen 17-setting WSB comparison."
},
"display_values": {
"YuE2": {
"quality_global_avg": 82.81723422675485,
"quality_musicality": 81.6295223219151,
"alignment": 84.59008050713697
},
"YuE2 (best-of-8)": {
"quality_global_avg": 88.34347258180588,
"quality_musicality": 90.0,
"alignment": 83.89142164823544
},
"ACE-Step 1.5": {
"quality_global_avg": 59.70424092683039,
"quality_musicality": 57.90284763591369,
"alignment": 74.06593383035025
},
"DiffRhythm 2": {
"quality_global_avg": 37.34582389095981,
"quality_musicality": 37.04192724997628,
"alignment": 53.17361182506653
},
"HeartMuLa": {
"quality_global_avg": 78.1413338271742,
"quality_musicality": 78.7417071724812,
"alignment": 38.373783402036175
},
"LeVo 2": {
"quality_global_avg": 69.67596261246808,
"quality_musicality": 67.6474792193652,
"alignment": 41.9279370903721
},
"MiniMax Music 2.6": {
"quality_global_avg": 71.0547991637534,
"quality_musicality": 68.70324225641005,
"alignment": 70.41355409197678
},
"MiniMax Music 3": {
"quality_global_avg": 70.24529112268468,
"quality_musicality": 66.41358422542463,
"alignment": 64.3979962976035
},
"Mureka 9": {
"quality_global_avg": 90.0,
"quality_musicality": 87.40608152985898,
"alignment": 77.87728582201137
},
"Muse": {
"quality_global_avg": 59.08947290000577,
"quality_musicality": 56.83882462017735,
"alignment": 62.30788899081859
},
"SongBloom": {
"quality_global_avg": 10.0,
"quality_musicality": 10.0,
"alignment": 10.0
},
"Suno v4.5": {
"quality_global_avg": 84.12555929249136,
"quality_musicality": 81.95902220989649,
"alignment": 77.67304060722402
},
"Suno v5": {
"quality_global_avg": 87.60060275113905,
"quality_musicality": 85.12156322510432,
"alignment": 90.0
},
"Suno v5.5": {
"quality_global_avg": 81.56516159216855,
"quality_musicality": 78.28738305243859,
"alignment": 81.72714762306776
},
"Suno v6": {
"quality_global_avg": 79.9972358228254,
"quality_musicality": 77.13274853053025,
"alignment": 85.0769639932043
},
"Suno v6 Wild": {
"quality_global_avg": 75.42328111548792,
"quality_musicality": 73.45561474186167,
"alignment": 85.41812210025412
},
"YuE 1": {
"quality_global_avg": 24.561036477434577,
"quality_musicality": 22.65806486519848,
"alignment": 31.798638200280863
}
},
"per_song_validation": {
"systems": 17,
"records": 3264,
"absolute_tolerance": 1e-10
},
"interpretation": [
"Descriptive standardized composites, not percentages or validated new evaluators.",
"Observed extrema map to 10 and 90 on 0–100 axes, leaving symmetric display margins.",
"All 15 external baselines, including HeartMuLa and both Suno v6 variants, define one frozen WSB reference.",
"YuE2 and Bo8 are excluded from the 15-system z-score standardization reference.",
"Q3O retains recorded prompt weights, which differ on some selected records.",
"Evaluator reuse and candidate-selection protocols remain as documented in Tables 1–2."
],
"source": "benchmark-results.csv",
"snapshot": "2026-09-12"
}