Difference between revisions of "2025:Music Reasoning QA Results"
From MIREX Wiki
Nicolaus526 (talk | contribs)  (→MMAR Results)  | 
				Nicolaus526 (talk | contribs)   (→OMniBench Results)  | 
				||
| (One intermediate revision by the same user not shown) | |||
| Line 4: | Line 4: | ||
|- style="font-weight:bold;"  | |- style="font-weight:bold;"  | ||
! System  | ! System  | ||
| − | |||
! style="text-align:right;" | ACC  | ! style="text-align:right;" | ACC  | ||
! style="text-align:right;" | music ACC  | ! style="text-align:right;" | music ACC  | ||
| Line 11: | Line 10: | ||
! style="text-align:right;" | mix-sound-music-speech  | ! style="text-align:right;" | mix-sound-music-speech  | ||
|-  | |-  | ||
| − | |||
| SAR-LM (w/ Qwen2.5-Omni)  | | SAR-LM (w/ Qwen2.5-Omni)  | ||
| style="text-align:right;" | 40.00%  | | style="text-align:right;" | 40.00%  | ||
| Line 19: | Line 17: | ||
| style="text-align:right;" | 37.50%  | | style="text-align:right;" | 37.50%  | ||
|-  | |-  | ||
| − | |||
| Qwen2.5-Omni  | | Qwen2.5-Omni  | ||
| style="text-align:right;" | 56.70%  | | style="text-align:right;" | 56.70%  | ||
| Line 26: | Line 23: | ||
| style="text-align:right;" | 67.07%  | | style="text-align:right;" | 67.07%  | ||
| style="text-align:right;" | 58.33%  | | style="text-align:right;" | 58.33%  | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
|}  | |}  | ||
| Line 41: | Line 30: | ||
|- style="font-weight:bold;"  | |- style="font-weight:bold;"  | ||
! System  | ! System  | ||
| − | |||
! style="text-align:right;" | ACC  | ! style="text-align:right;" | ACC  | ||
! style="text-align:right;" | music ACC  | ! style="text-align:right;" | music ACC  | ||
|-  | |-  | ||
| − | |||
| SAR-LM (w/ Qwen2.5-Omni)  | | SAR-LM (w/ Qwen2.5-Omni)  | ||
| style="text-align:right;" | 31.26%  | | style="text-align:right;" | 31.26%  | ||
| style="text-align:right;" | 41.50%  | | style="text-align:right;" | 41.50%  | ||
|-  | |-  | ||
| − | |||
| Qwen2-Audio-7B-Instruct  | | Qwen2-Audio-7B-Instruct  | ||
| style="text-align:right;" | 40.72%  | | style="text-align:right;" | 40.72%  | ||
Latest revision as of 01:32, 16 September 2025
MMAR Results
| System | ACC | music ACC | mix-sound-music | mix-music-speech | mix-sound-music-speech | 
|---|---|---|---|---|---|
| SAR-LM (w/ Qwen2.5-Omni) | 40.00% | 33.98% | 27.27% | 48.78% | 37.50% | 
| Qwen2.5-Omni | 56.70% | 40.78% | 54.55% | 67.07% | 58.33% | 
OMniBench Results
| System | ACC | music ACC | 
|---|---|---|
| SAR-LM (w/ Qwen2.5-Omni) | 31.26% | 41.50% | 
| Qwen2-Audio-7B-Instruct | 40.72% | 38.68% |