TASK |
DATASET |
MODEL |
METRIC NAME |
METRIC VALUE |
GLOBAL RANK |
REMOVE |
Temporal Relation Extraction
|
Vinoground
|
LLaVA-NeXT-Video-34B (CoT)
|
Text Score
|
25.8
|
# 14
|
|
Temporal Relation Extraction
|
Vinoground
|
LLaVA-NeXT-Video-34B (CoT)
|
Video Score
|
22.2
|
# 18
|
|
Temporal Relation Extraction
|
Vinoground
|
LLaVA-NeXT-Video-34B (CoT)
|
Group Score
|
5.2
|
# 19
|
|
Temporal Relation Extraction
|
Vinoground
|
Phi-3.5-Vision
|
Text Score
|
24
|
# 16
|
|
Temporal Relation Extraction
|
Vinoground
|
Phi-3.5-Vision
|
Video Score
|
22.4
|
# 17
|
|
Temporal Relation Extraction
|
Vinoground
|
Phi-3.5-Vision
|
Group Score
|
6.2
|
# 17
|
|
Temporal Relation Extraction
|
Vinoground
|
LLaVA-NeXT-Video-7B
|
Text Score
|
21.8
|
# 19
|
|
Temporal Relation Extraction
|
Vinoground
|
LLaVA-NeXT-Video-7B
|
Video Score
|
25.6
|
# 13
|
|
Temporal Relation Extraction
|
Vinoground
|
LLaVA-NeXT-Video-7B
|
Group Score
|
6.2
|
# 17
|
|
Temporal Relation Extraction
|
Vinoground
|
LLaVA-NeXT-Video-7B (CoT)
|
Text Score
|
21.8
|
# 19
|
|
Temporal Relation Extraction
|
Vinoground
|
LLaVA-NeXT-Video-7B (CoT)
|
Video Score
|
26.2
|
# 11
|
|
Temporal Relation Extraction
|
Vinoground
|
LLaVA-NeXT-Video-7B (CoT)
|
Group Score
|
6.8
|
# 14
|
|
Temporal Relation Extraction
|
Vinoground
|
LLaVA-NeXT-Video-34B
|
Text Score
|
23
|
# 18
|
|
Temporal Relation Extraction
|
Vinoground
|
LLaVA-NeXT-Video-34B
|
Video Score
|
21.2
|
# 20
|
|
Temporal Relation Extraction
|
Vinoground
|
LLaVA-NeXT-Video-34B
|
Group Score
|
3.8
|
# 20
|
|
Temporal Relation Extraction
|
Vinoground
|
Claude 3.5 Sonnet
|
Text Score
|
32.8
|
# 10
|
|
Temporal Relation Extraction
|
Vinoground
|
Claude 3.5 Sonnet
|
Video Score
|
28.8
|
# 7
|
|
Temporal Relation Extraction
|
Vinoground
|
Claude 3.5 Sonnet
|
Group Score
|
10.6
|
# 9
|
|
Read more here: Source link