Add PBench average evaluation result
#3
by merve HF Staff - opened
- .eval_results/pbench.yaml +4 -51
.eval_results/pbench.yaml
CHANGED
|
@@ -1,56 +1,9 @@
|
|
| 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-
|
| 54 |
source:
|
| 55 |
-
url: https://
|
| 56 |
-
name:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
- dataset:
|
| 2 |
id: tiiuae/PBench
|
| 3 |
task_id: average
|
| 4 |
value: 57.0
|
| 5 |
+
date: '2026-05-11'
|
| 6 |
source:
|
| 7 |
+
url: https://huggingface.co/tiiuae/Falcon-Perception
|
| 8 |
+
name: Community Evals
|
| 9 |
+
user: merve
|