yasserDahou commited on
Commit
505adaa
·
verified ·
1 Parent(s): 460b089

Add PBench evaluation results

Browse files
Files changed (1) hide show
  1. .eval_results/pbench.yaml +56 -0
.eval_results/pbench.yaml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: tiiuae/PBench
3
+ task_id: level_0
4
+ value: 65.1
5
+ date: '2026-03-28'
6
+ source:
7
+ url: https://arxiv.org/abs/2603.27365
8
+ name: Falcon Perception paper
9
+ - dataset:
10
+ id: tiiuae/PBench
11
+ task_id: level_1
12
+ value: 63.6
13
+ date: '2026-03-28'
14
+ source:
15
+ url: https://arxiv.org/abs/2603.27365
16
+ name: Falcon Perception paper
17
+ - dataset:
18
+ id: tiiuae/PBench
19
+ task_id: level_2
20
+ value: 38.0
21
+ date: '2026-03-28'
22
+ source:
23
+ url: https://arxiv.org/abs/2603.27365
24
+ name: Falcon Perception paper
25
+ - dataset:
26
+ id: tiiuae/PBench
27
+ task_id: level_3
28
+ value: 53.5
29
+ date: '2026-03-28'
30
+ source:
31
+ url: https://arxiv.org/abs/2603.27365
32
+ name: Falcon Perception paper
33
+ - dataset:
34
+ id: tiiuae/PBench
35
+ task_id: level_4
36
+ value: 49.1
37
+ date: '2026-03-28'
38
+ source:
39
+ url: https://arxiv.org/abs/2603.27365
40
+ name: Falcon Perception paper
41
+ - dataset:
42
+ id: tiiuae/PBench
43
+ task_id: dense
44
+ value: 72.6
45
+ date: '2026-03-28'
46
+ source:
47
+ url: https://arxiv.org/abs/2603.27365
48
+ name: Falcon Perception paper
49
+ - dataset:
50
+ id: tiiuae/PBench
51
+ task_id: average
52
+ value: 57.0
53
+ date: '2026-03-28'
54
+ source:
55
+ url: https://arxiv.org/abs/2603.27365
56
+ name: Falcon Perception paper