Text-to-Audio Evaluation on PAM (test)
0.609LCCCAF-Score
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=Qwen2.5-7B, Audio Encoder=M2D2026.03 | 0.609 | 0.598 | 0.43 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=Qwen3, Audio Encoder=M2D2026.03 | 0.608 | 0.606 | 0.436 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=Qwen3, Audio Encoder=MGA2026.03 | 0.596 | 0.579 | 0.412 | |
| AQA-ScoreFramework=AQA-Score (LALM-ONLY), Backbone=AF3-think2026.03 | 0.582 | 0.587 | 0.419 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=Qwen3, Audio Encoder=LAION2026.03 | 0.582 | 0.572 | 0.407 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=Qwen2.5-7B, Audio Encoder=MGA2026.03 | 0.57 | 0.551 | 0.392 | |
| M2D-CLAPFramework=CLAPScore (CLAP-ONLY)2026.03 | 0.566 | 0.548 | 0.388 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=Qwen2.5-3B, Audio Encoder=MGA2026.03 | 0.559 | 0.545 | 0.389 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=Qwen2.5-3B, Audio Encoder=M2D2026.03 | 0.556 | 0.543 | 0.388 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=AF3, Audio Encoder=M2D2026.03 | 0.544 | 0.543 | 0.383 | |
| AQA-ScoreFramework=AQA-Score (LALM-ONLY), Backbone=Qwen-2.5-Omni-3B2026.03 | 0.54 | 0.56 | 0.41 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=Qwen2.5-3B, Audio Encoder=LAION2026.03 | 0.538 | 0.526 | 0.372 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=AF3, Audio Encoder=MGA2026.03 | 0.534 | 0.522 | 0.368 | |
| MGA-CLAPFramework=CLAPScore (CLAP-ONLY)2026.03 | 0.532 | 0.522 | 0.368 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=Qwen3, Audio Encoder=MS2026.03 | 0.521 | 0.483 | 0.34 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=Qwen2.5-7B, Audio Encoder=LAION2026.03 | 0.519 | 0.506 | 0.356 | |
| AQA-ScoreFramework=AQA-Score (LALM-ONLY), Backbone=Qwen-2.5-Omni-7B2026.03 | 0.518 | 0.589 | 0.429 | |
| AQA-ScoreFramework=AQA-Score (LALM-ONLY), Backbone=AF3-base2026.03 | 0.496 | 0.538 | 0.383 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=Qwen2.5-3B, Audio Encoder=MS2026.03 | 0.485 | 0.451 | 0.316 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=AF3, Audio Encoder=LAION2026.03 | 0.472 | 0.459 | 0.319 | |
| LAION-CLAPFramework=CLAPScore (CLAP-ONLY)2026.03 | 0.461 | 0.452 | 0.314 | |
| FLEURFramework=LALM-ONLY, Backbone=Qwen3-Omni-Instruct2026.03 | 0.458 | 0.426 | 0.297 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=Qwen2.5-7B, Audio Encoder=MS2026.03 | 0.437 | 0.4 | 0.278 | |
| Raw ScoreFramework=LALM-ONLY, Backbone=Qwen3-Omni-Instruct2026.03 | 0.42 | 0.384 | 0.299 | |
| FLEURFramework=LALM-ONLY, Backbone=Qwen-2.5-Omni-7B2026.03 | 0.418 | 0.429 | 0.302 | |
| Raw ScoreFramework=LALM-ONLY, Backbone=Qwen-2.5-Omni-3B2026.03 | 0.376 | 0.364 | 0.287 | |
| FLEURFramework=LALM-ONLY, Backbone=Qwen-2.5-Omni-3B2026.03 | 0.372 | 0.411 | 0.288 | |
| Raw ScoreFramework=LALM-ONLY, Backbone=Qwen3-Omni-Thinking2026.03 | 0.369 | 0.362 | 0.276 | |
| FLEURFramework=LALM-ONLY, Backbone=Qwen3-Omni-Think2026.03 | 0.367 | 0.351 | 0.242 | |
| CAF-ScoreFramework=CAF-Score (CLAP + LALM), Backbone=AF3, Audio Encoder=MS2026.03 | 0.362 | 0.324 | 0.223 | |
| MS-CLAPFramework=CLAPScore (CLAP-ONLY)2026.03 | 0.345 | 0.312 | 0.215 | |
| Raw ScoreFramework=LALM-ONLY, Backbone=Qwen-2.5-Omni-7B2026.03 | 0.305 | 0.299 | 0.302 | |
| FLEURFramework=LALM-ONLY, Backbone=AF3-Base2026.03 | 0.152 | 0.194 | 0.132 | |
| Raw ScoreFramework=LALM-ONLY, Backbone=AF3-Base2026.03 | 0.126 | 0.089 | 0.132 | |
| FLEURFramework=LALM-ONLY, Backbone=AF3-Think2026.03 | -0.025 | -0.042 | -0.029 | |
| Raw ScoreFramework=LALM-ONLY, Backbone=AF3-Think2026.03 | -0.07 | -0.062 | -0.049 |