lwpyh commited on
Commit
4fba015
·
verified ·
1 Parent(s): 45ca53b

Upload 4 files

Browse files
Files changed (4) hide show
  1. leaderboard.csv +15 -15
  2. leaderboard_chain1.csv +15 -15
  3. leaderboard_chain2.csv +15 -15
  4. results.csv +6 -6
leaderboard.csv CHANGED
@@ -1,16 +1,16 @@
1
  Model,All,All,Short,Short,Medium,Medium,Long,Long
2
- ,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM
3
- Gemini-2-Flash,26.87,35.57,24.97,32.07,28.99,40.35,37.81,56.14
4
- GPT-4o,26.75,38.15,27.49,38.56,26.96,40.58,14.86,19.28
5
- Qwen2.5-VL,23.96,32.39,25.51,34.84,23.67,32.87,2.2,2.27
6
- Video-Llama3,21.66,27.04,21.68,26.62,21.84,27.23,22.46,28.83
7
- Llava-Video,20.82,27.33,22.37,30.23,18.28,22.77,18.23,25.23
8
- Video-CCAM-v1.2,20.41,30.7,21.66,34.09,19.62,28.36,12.61,15.8
9
- VTimeLLM,17.71,22.04,18.31,23.19,18.15,22.44,5.52,5.89
10
- InternVL-2.5,17.6,24.92,17.94,22.9,17.94,23.06,9.58,11.19
11
- Sa2VA,17.11,20.31,18.14,22.01,16.32,18.92,8.85,9.7
12
- VideoChat2,17.02,20.26,17.57,21.02,17.2,20.5,5.28,5.64
13
- Qwen2-VL,16.71,18.79,15.78,17.5,18.47,21.22,14.09,17.53
14
- Oryx-1.5,15.11,13.83,13.17,14.25,14.83,16.46,11.89,13.99
15
- TimeChat,13.07,14.78,13.7,15.56,13.22,15.06,3.24,3.37
16
- TRACE,12.01,13.25,11.77,12.96,12.49,13.87,13.59,15.3
 
1
  Model,All,All,Short,Short,Medium,Medium,Long,Long
2
+ ,mLGM,mAM,mAM,mLGM,mAM,mLGM,mAM,mLGM
3
+ GPT-4o,38.15,26.75,27.49,38.56,26.96,40.58,14.86,19.28
4
+ Gemini-2-Flash,35.57,26.87,24.97,32.07,28.99,40.35,37.81,56.14
5
+ Qwen2.5-VL,32.39,23.96,25.51,34.84,23.67,32.87,2.2,2.27
6
+ Video-CCAM-v1.2,30.7,20.41,21.66,34.09,19.62,28.36,12.61,15.8
7
+ Llava-Video,27.33,20.82,22.37,30.23,18.28,22.77,18.23,25.23
8
+ Video-Llama3,27.04,21.66,21.68,26.62,21.84,27.23,22.46,28.83
9
+ InternVL-2.5,24.92,17.6,17.94,22.9,17.94,23.06,9.58,11.19
10
+ VTimeLLM,22.04,17.71,18.31,23.19,18.15,22.44,5.52,5.89
11
+ Sa2VA,20.31,17.11,18.14,22.01,16.32,18.92,8.85,9.7
12
+ VideoChat2,20.26,17.02,17.57,21.02,17.2,20.5,5.28,5.64
13
+ Qwen2-VL,18.79,16.71,15.78,17.5,18.47,21.22,14.09,17.53
14
+ TimeChat,14.78,13.07,13.7,15.56,13.22,15.06,3.24,3.37
15
+ Oryx-1.5,13.83,15.11,13.17,14.25,14.83,16.46,11.89,13.99
16
+ TRACE,13.25,12.01,11.77,12.96,12.49,13.87,13.59,15.3
leaderboard_chain1.csv CHANGED
@@ -1,15 +1,15 @@
1
2
- GPT-4o,1.71,60.78,23.14,10.35,5.10,16.67,19.92,8.36,2.75,6.47,39.51,27.97
3
- Gemini-2-Flash,1.59,53.01,31.63,15.84,9.45,24.54,15.67,3.82,0.93,4.63,36.14,27.39
4
- Video-Llama3,1.38,41.94,35.73,19.80,8.68,22.97,3.17,0.76,0.11,0.89,27.12,21.93
5
- Qwen2.5-VL,1.61,54.53,17.03,8.92,3.72,11.48,35.89,19.92,8.36,13.59,35.20,26.53
6
- Qwen2-VL,1.03,25.91,27.96,17.94,9.16,19.18,28.59,12.21,3.89,9.31,20.35,18.13
7
- InternVL-2.5,1.46,44.18,11.98,4.87,2.34,8.72,2.18,0.27,0.04,0.65,22.69,17.85
8
- Llava-Video,1.50,49.48,15.12,6.30,1.43,10.52,5.23,0.94,0.18,1.92,27.11,20.64
9
- VideoChat2,1.27,36.21,20.47,13.07,6.49,13.69,10.06,1.31,0.14,2.51,20.74,17.47
10
- Oryx-1.5,0.94,20.47,17.03,4.48,1.72,13.54,35.58,11.60,2.17,10.14,16.05,14.72
11
- Video-CCAM-v1.2,1.75,59.35,1.15,0.00,0.00,1.50,0.00,0.00,0.00,0.00,30.51,20.28
12
- TimeChat,1.06,26.38,17.80,8.68,3.48,12.01,0.00,0.00,0.00,0.00,14.47,12.80
13
- VTimeLLM,1.45,41.46,25.24,10.88,3.15,17.13,0.62,0.14,0.03,0.21,24.18,19.60
14
- TRACE,0.90,17.60,28.53,14.17,6.73,19.74,0.00,0.00,0.00,0.00,13.78,12.45
15
- Sa2VA,0.70,16.36,0.10,0.00,0.00,0.11,52.16,42.68,34.18,32.31,19.00,16.26
 
1
2
+ GPT-4o,39.51,27.97,1.71,60.78,23.14,10.35,5.1,16.67,19.92,8.36,2.75,6.47
3
+ Gemini-2-Flash,36.14,27.39,1.59,53.01,31.63,15.84,9.45,24.54,15.67,3.82,0.93,4.63
4
+ Qwen2.5-VL,35.2,26.53,1.61,54.53,17.03,8.92,3.72,11.48,35.89,19.92,8.36,13.59
5
+ Video-CCAM-v1.2,30.51,20.28,1.75,59.35,1.15,0,0,1.5,0,0,0,0
6
+ Video-Llama3,27.12,21.93,1.38,41.94,35.73,19.8,8.68,22.97,3.17,0.76,0.11,0.89
7
+ Llava-Video,27.11,20.64,1.5,49.48,15.12,6.3,1.43,10.52,5.23,0.94,0.18,1.92
8
+ VTimeLLM,24.18,19.6,1.45,41.46,25.24,10.88,3.15,17.13,0.62,0.14,0.03,0.21
9
+ InternVL-2.5,22.69,17.85,1.46,44.18,11.98,4.87,2.34,8.72,2.18,0.27,0.04,0.65
10
+ VideoChat2,20.74,17.47,1.27,36.21,20.47,13.07,6.49,13.69,10.06,1.31,0.14,2.51
11
+ Qwen2-VL,20.35,18.13,1.03,25.91,27.96,17.94,9.16,19.18,28.59,12.21,3.89,9.31
12
+ Sa2VA,19,16.26,0.7,16.36,0.1,0,0,0.11,52.16,42.68,34.18,32.31
13
+ Oryx-1.5,16.05,14.72,0.94,20.47,17.03,4.48,1.72,13.54,35.58,11.6,2.17,10.14
14
+ TimeChat,14.47,12.8,1.06,26.38,17.8,8.68,3.48,12.01,0,0,0,0
15
+ TRACE,13.78,12.45,0.9,17.6,28.53,14.17,6.73,19.74,0,0,0,0
leaderboard_chain2.csv CHANGED
@@ -1,15 +1,15 @@
1
2
- GPT-4o,1.71,60.78,9.29,4.18,1.19,3.01,17.13,10.04,7.25,12.82,36.79,25.53
3
- Gemini-2-Flash,1.59,53.01,7.49,1.89,0.58,2.21,31.58,15.22,8.54,23.83,34.99,26.35
4
- Video-Llama3,1.38,41.94,0.62,0.17,0.02,0.19,35.11,20.42,9.21,23.14,26.96,21.76
5
- Qwen2.5-VL,1.61,54.53,5.15,2.87,1.40,2.00,11.02,5.39,2.48,7.61,29.58,21.38
6
- Qwen2-VL,1.03,25.91,7.11,3.55,1.14,2.41,24.62,16.32,8.25,17.52,17.23,15.28
7
- InternVL-2.5,1.46,44.18,0.42,0.03,0.00,0.14,10.83,3.77,1.57,7.75,27.15,17.36
8
- Llava-Video,1.50,49.48,4.29,1.23,0.25,1.31,16.89,5.49,2.00,12.21,27.54,21.00
9
- VideoChat2,1.27,36.21,3.08,0.91,0.30,0.97,18.08,12.07,6.20,12.50,19.77,16.56
10
- Oryx-1.5,0.94,20.47,11.50,4.32,0.96,3.50,18.99,5.58,2.72,14.81,14.16,12.93
11
- Video-CCAM-v1.2,1.75,59.35,0.00,0.00,0.00,0.00,2.19,0.00,0.00,2.26,30.88,20.54
12
- TimeChat,1.06,26.38,0.00,0.00,0.00,0.00,20.42,8.54,2.53,13.60,15.08,13.33
13
- VTimeLLM,1.45,41.46,0.00,0.00,0.00,0.00,8.44,4.53,2.10,5.96,19.90,15.81
14
- TRACE,0.90,17.60,0.00,0.00,0.00,0.00,24.52,12.02,5.73,17.11,12.71,11.57
15
- Sa2VA,0.70,16.36,58.47,49.47,40.42,37.48,0.00,0.00,0.00,0.00,21.61,17.95
 
1
2
+ GPT-4o,36.79,25.53,1.71,60.78,9.29,4.18,1.19,3.01,17.13,10.04,7.25,12.82
3
+ Gemini-2-Flash,34.99,26.35,1.59,53.01,7.49,1.89,0.58,2.21,31.58,15.22,8.54,23.83
4
+ Video-CCAM-v1.2,30.88,20.54,1.75,59.35,0,0,0,0,2.19,0,0,2.26
5
+ Qwen2.5-VL,29.58,21.38,1.61,54.53,5.15,2.87,1.4,2,11.02,5.39,2.48,7.61
6
+ Llava-Video,27.54,21,1.5,49.48,4.29,1.23,0.25,1.31,16.89,5.49,2,12.21
7
+ InternVL-2.5,27.15,17.36,1.46,44.18,0.42,0.03,0,0.14,10.83,3.77,1.57,7.75
8
+ Video-Llama3,26.96,21.76,1.38,41.94,0.62,0.17,0.02,0.19,35.11,20.42,9.21,23.14
9
+ Sa2VA,21.61,17.95,0.7,16.36,58.47,49.47,40.42,37.48,0,0,0,0
10
+ VTimeLLM,19.9,15.81,1.45,41.46,0,0,0,0,8.44,4.53,2.1,5.96
11
+ VideoChat2,19.77,16.56,1.27,36.21,3.08,0.91,0.3,0.97,18.08,12.07,6.2,12.5
12
+ Qwen2-VL,17.23,15.28,1.03,25.91,7.11,3.55,1.14,2.41,24.62,16.32,8.25,17.52
13
+ TimeChat,15.08,13.33,1.06,26.38,0,0,0,0,20.42,8.54,2.53,13.6
14
+ Oryx-1.5,14.16,12.93,0.94,20.47,11.5,4.32,0.96,3.5,18.99,5.58,2.72,14.81
15
+ TRACE,12.71,11.57,0.9,17.6,0,0,0,0,24.52,12.02,5.73,17.11
results.csv CHANGED
@@ -2,15 +2,15 @@
2
  ,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM
3
  GPT-4o,29.18,42.13,31.04,45.14,26.96,38.5,26.61,37.82,26.5,36.36,28.47,46.41,26.89,37.29,24.01,31.16,16.68,22.3
4
  Gemini-2-Flash,27.78,36.26,23.42,28.58,28.79,38.39,23.73,29.81,24.35,31.26,33.35,52,24.8,31.59,22.28,27.43,38.33,56.62
5
- Video-Llama3,21.43,26.1,24.37,31.35,24.13,31.12,18.74,22.1,22.41,28.51,24.7,31.58,23.15,29.17,20,24.43,24.68,33.74
6
  Qwen2.5-VL,26.32,36.26,27.07,38.12,23.74,32.13,26.1,35.92,23.24,31.39,20.52,27.36,29.94,33.52,25.61,35.04,2.76,2.87
7
- Qwen2-VL,16.57,18.34,16.46,18.37,21.85,27.75,12.8,13.81,16.34,18.59,20.75,24.82,16.41,18.59,15.1,16.69,17.29,22.23
 
 
8
  InternVL-2.5,20.98,28.59,17.74,22.44,20.1,28.76,17.7,22.67,18.86,24.98,15.34,18.59,20.31,27.1,17.72,22.49,9.35,10.76
9
  Llava-Video,20.34,25.96,24.57,33.88,25.03,37.03,20.08,25.58,21.33,28.78,20.24,27.1,23.76,34.2,20.07,25.4,21.97,32.82
10
  VideoChat2,18.5,22.58,20.23,25.05,19.11,24.67,16.03,18.98,16.88,20.23,18.27,21.46,15.91,18.93,15.68,18.65,7.09,7.6
11
- Oryx-1.5,13.58,14.7,11.05,11.83,20,24.4,9.82,10.39,14.39,16.03,16.14,18.85,14.09,15.43,14.3,15.6,10.34,11.78
12
- Video-CCAM-v1.2,23.47,39.49,26.19,50.25,28.54,56.27,19.96,29.73,21.99,35.18,16.42,22.06,25.59,46.08,21.22,32.89,15.03,19.89
13
  TimeChat,18.26,22.52,12.61,14.14,13.75,15.86,12.48,14.02,13.63,15.64,11.17,12.27,15.46,18.22,13.7,15.64,6.05,6.53
 
14
  VTimeLLM,14.54,16.93,20.28,26.24,22.93,33.5,20.33,27.43,16.12,19.99,15.65,18.46,18.12,23.4,18.36,22.88,8.67,9.56
15
- TRACE,12.35,13.77,10.28,11.23,18.85,22.75,8.59,9.25,15.31,17.41,13.99,15.72,12.87,14.32,10.91,11.92,15.19,17.34
16
- Sa2VA,21.01,27.03,13.62,16.6,23.38,29.13,17.89,23.25,17.01,19.69,13.28,14.9,21.36,26.25,18.44,22.96,10.91,11.97
 
2
  ,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM,mAM,mLGM
3
  GPT-4o,29.18,42.13,31.04,45.14,26.96,38.5,26.61,37.82,26.5,36.36,28.47,46.41,26.89,37.29,24.01,31.16,16.68,22.3
4
  Gemini-2-Flash,27.78,36.26,23.42,28.58,28.79,38.39,23.73,29.81,24.35,31.26,33.35,52,24.8,31.59,22.28,27.43,38.33,56.62
 
5
  Qwen2.5-VL,26.32,36.26,27.07,38.12,23.74,32.13,26.1,35.92,23.24,31.39,20.52,27.36,29.94,33.52,25.61,35.04,2.76,2.87
6
+ Video-CCAM-v1.2,23.47,39.49,26.19,50.25,28.54,56.27,19.96,29.73,21.99,35.18,16.42,22.06,25.59,46.08,21.22,32.89,15.03,19.89
7
+ Video-Llama3,21.43,26.1,24.37,31.35,24.13,31.12,18.74,22.1,22.41,28.51,24.7,31.58,23.15,29.17,20,24.43,24.68,33.74
8
+ Sa2VA,21.01,27.03,13.62,16.6,23.38,29.13,17.89,23.25,17.01,19.69,13.28,14.9,21.36,26.25,18.44,22.96,10.91,11.97
9
  InternVL-2.5,20.98,28.59,17.74,22.44,20.1,28.76,17.7,22.67,18.86,24.98,15.34,18.59,20.31,27.1,17.72,22.49,9.35,10.76
10
  Llava-Video,20.34,25.96,24.57,33.88,25.03,37.03,20.08,25.58,21.33,28.78,20.24,27.1,23.76,34.2,20.07,25.4,21.97,32.82
11
  VideoChat2,18.5,22.58,20.23,25.05,19.11,24.67,16.03,18.98,16.88,20.23,18.27,21.46,15.91,18.93,15.68,18.65,7.09,7.6
 
 
12
  TimeChat,18.26,22.52,12.61,14.14,13.75,15.86,12.48,14.02,13.63,15.64,11.17,12.27,15.46,18.22,13.7,15.64,6.05,6.53
13
+ Qwen2-VL,16.57,18.34,16.46,18.37,21.85,27.75,12.8,13.81,16.34,18.59,20.75,24.82,16.41,18.59,15.1,16.69,17.29,22.23
14
  VTimeLLM,14.54,16.93,20.28,26.24,22.93,33.5,20.33,27.43,16.12,19.99,15.65,18.46,18.12,23.4,18.36,22.88,8.67,9.56
15
+ Oryx-1.5,13.58,14.7,11.05,11.83,20,24.4,9.82,10.39,14.39,16.03,16.14,18.85,14.09,15.43,14.3,15.6,10.34,11.78
16
+ TRACE,12.35,13.77,10.28,11.23,18.85,22.75,8.59,9.25,15.31,17.41,13.99,15.72,12.87,14.32,10.91,11.92,15.19,17.34