Spaces:
Running
Running
new results
Browse files
ZeroEval-main/result_dirs/zebra-grid.summary.json
CHANGED
|
@@ -1,4 +1,15 @@
|
|
| 1 |
[
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
{
|
| 3 |
"Model": "o1-mini-2024-09-12",
|
| 4 |
"Mode": "greedy",
|
|
|
|
| 1 |
[
|
| 2 |
+
{
|
| 3 |
+
"Model": "o1-preview-2024-09-12",
|
| 4 |
+
"Mode": "greedy",
|
| 5 |
+
"Puzzle Acc": "71.40",
|
| 6 |
+
"Cell Acc": "75.14",
|
| 7 |
+
"No answer": "0.30",
|
| 8 |
+
"Easy Puzzle Acc": "98.57",
|
| 9 |
+
"Hard Puzzle Acc": "60.83",
|
| 10 |
+
"Total Puzzles": 1000,
|
| 11 |
+
"Reason Lens": "1565.88"
|
| 12 |
+
},
|
| 13 |
{
|
| 14 |
"Model": "o1-mini-2024-09-12",
|
| 15 |
"Mode": "greedy",
|