Spaces:
Running
Running
Update ZeroEval-main/result_dirs/zebra-grid.summary.json
Browse files
ZeroEval-main/result_dirs/zebra-grid.summary.json
CHANGED
@@ -1,4 +1,38 @@
|
|
1 |
[
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
{
|
3 |
"Model": "o1-2024-12-17",
|
4 |
"Mode": "greedy",
|
@@ -33,6 +67,23 @@
|
|
33 |
"N_Mode": "single",
|
34 |
"N_Size": 1
|
35 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
{
|
37 |
"Model": "o1-preview-2024-09-12",
|
38 |
"Mode": "greedy",
|
|
|
1 |
[
|
2 |
+
{
|
3 |
+
"Model": "o3-mini-2025-01-31-high",
|
4 |
+
"Mode": "greedy",
|
5 |
+
"Puzzle Acc": "91.70",
|
6 |
+
"Cell Acc": "95.70",
|
7 |
+
"No answer": "0.30",
|
8 |
+
"Easy Puzzle Acc": "99.64",
|
9 |
+
"Hard Puzzle Acc": "88.61",
|
10 |
+
"Small Puzzle Acc": "99.69",
|
11 |
+
"Medium Puzzle Acc": "97.14",
|
12 |
+
"Large Puzzle Acc": "87.50",
|
13 |
+
"XL Puzzle Acc": "75.50",
|
14 |
+
"Total Puzzles": 1000,
|
15 |
+
"Reason Lens": "1983.34",
|
16 |
+
"N_Mode": "single",
|
17 |
+
"N_Size": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"Model": "o3-mini-2025-01-31-medium",
|
21 |
+
"Mode": "greedy",
|
22 |
+
"Puzzle Acc": "88.90",
|
23 |
+
"Cell Acc": "90.41",
|
24 |
+
"No answer": "0.10",
|
25 |
+
"Easy Puzzle Acc": "99.64",
|
26 |
+
"Hard Puzzle Acc": "84.72",
|
27 |
+
"Small Puzzle Acc": "99.69",
|
28 |
+
"Medium Puzzle Acc": "97.86",
|
29 |
+
"Large Puzzle Acc": "88.00",
|
30 |
+
"XL Puzzle Acc": "60.00",
|
31 |
+
"Total Puzzles": 1000,
|
32 |
+
"Reason Lens": "2067.98",
|
33 |
+
"N_Mode": "single",
|
34 |
+
"N_Size": 1
|
35 |
+
},
|
36 |
{
|
37 |
"Model": "o1-2024-12-17",
|
38 |
"Mode": "greedy",
|
|
|
67 |
"N_Mode": "single",
|
68 |
"N_Size": 1
|
69 |
},
|
70 |
+
{
|
71 |
+
"Model": "o3-mini-2025-01-31-low",
|
72 |
+
"Mode": "greedy",
|
73 |
+
"Puzzle Acc": "74.80",
|
74 |
+
"Cell Acc": "72.60",
|
75 |
+
"No answer": "1.60",
|
76 |
+
"Easy Puzzle Acc": "99.29",
|
77 |
+
"Hard Puzzle Acc": "65.28",
|
78 |
+
"Small Puzzle Acc": "99.38",
|
79 |
+
"Medium Puzzle Acc": "91.07",
|
80 |
+
"Large Puzzle Acc": "64.50",
|
81 |
+
"XL Puzzle Acc": "23.00",
|
82 |
+
"Total Puzzles": 1000,
|
83 |
+
"Reason Lens": "2080.78",
|
84 |
+
"N_Mode": "single",
|
85 |
+
"N_Size": 1
|
86 |
+
},
|
87 |
{
|
88 |
"Model": "o1-preview-2024-09-12",
|
89 |
"Mode": "greedy",
|