Text-to-Audio temporal grounding on ChronusAV benchmark leaderboard · SOTA2 Research

Text-to-Audio temporal grounding on ChronusAV

7.4BLEU-4PadCaptioner

Evaluation Results

Method	Links
PadCaptioner2026.07		7.4	7.3	4.8	35.1
ChronusOmni2026.07		6.8	6.9	4.5	34.3
ChronusOmni2025.12		6.78	6.86	4.5	34.3
Qwen3-Omni2025.12		0.94	2.26	1.2	2.18
Qwen3-Omni2026.07		0.9	2.3	1.2	2.2
Qwen2.5-Omni2026.07		0.7	1	0.6	0.3
Qwen2.5-Omni2025.12		0.67	1.01	0.64	0.26
Ola2026.07		0.2	0.8	0.3	0.3
LongVALE-LLM2026.07		0.2	1.3	0.5	0.2
ARC-HY-Video2026.07		0.2	1.2	0.7	0.4
Ola2025.12		0.18	0.78	0.31	0.26
ARC-Hunyuan-Video2025.12		0.18	1.17	0.65	0.37
LongVALE-LLM2025.12		0.15	1.31	0.5	0.19
VideoLLaMA2026.07		0.1	1.1	0.6	0.1
VideoLLaMA2025.12		0.05	1.13	0.63	0.06
AVicuna2025.12		0.01	0.51	0.13	0.02
AVicuna2026.07		0	0.5	0.1	0