Spaces:
Running
Running
Update ZeroEval-main/result_dirs/zebra-grid.summary.json
Browse fileshttps://github.com/WildEval/ZeroEval/blob/main/result_dirs/zebra-grid.summary.md
ZeroEval-main/result_dirs/zebra-grid.summary.json
CHANGED
|
@@ -1,4 +1,21 @@
|
|
| 1 |
[
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
{
|
| 3 |
"Model": "o3-mini-2025-01-31-high",
|
| 4 |
"Mode": "greedy",
|
|
@@ -50,6 +67,23 @@
|
|
| 50 |
"N_Mode": "single",
|
| 51 |
"N_Size": 1
|
| 52 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
{
|
| 54 |
"Model": "deepseek-R1",
|
| 55 |
"Mode": "greedy",
|
|
|
|
| 1 |
[
|
| 2 |
+
{
|
| 3 |
+
"Model": "grok-3-mini-fast-beta-high",
|
| 4 |
+
"Mode": "greedy",
|
| 5 |
+
"Puzzle Acc": "92.60",
|
| 6 |
+
"Cell Acc": "94.63",
|
| 7 |
+
"No answer": "1.00",
|
| 8 |
+
"Easy Puzzle Acc": "98.93",
|
| 9 |
+
"Hard Puzzle Acc": "90.14",
|
| 10 |
+
"Small Puzzle Acc": "98.75",
|
| 11 |
+
"Medium Puzzle Acc": "96.43",
|
| 12 |
+
"Large Puzzle Acc": "93.50",
|
| 13 |
+
"XL Puzzle Acc": "76.50",
|
| 14 |
+
"Total Puzzles": 1000,
|
| 15 |
+
"Reason Lens": "782.25",
|
| 16 |
+
"N_Mode": "single",
|
| 17 |
+
"N_Size": 1
|
| 18 |
+
},
|
| 19 |
{
|
| 20 |
"Model": "o3-mini-2025-01-31-high",
|
| 21 |
"Mode": "greedy",
|
|
|
|
| 67 |
"N_Mode": "single",
|
| 68 |
"N_Size": 1
|
| 69 |
},
|
| 70 |
+
{
|
| 71 |
+
"Model": "grok-3-mini-fast-beta-low",
|
| 72 |
+
"Mode": "greedy",
|
| 73 |
+
"Puzzle Acc": "80.70",
|
| 74 |
+
"Cell Acc": "84.22",
|
| 75 |
+
"No answer": "0.00",
|
| 76 |
+
"Easy Puzzle Acc": "98.57",
|
| 77 |
+
"Hard Puzzle Acc": "73.75",
|
| 78 |
+
"Small Puzzle Acc": "98.75",
|
| 79 |
+
"Medium Puzzle Acc": "96.43",
|
| 80 |
+
"Large Puzzle Acc": "77.00",
|
| 81 |
+
"XL Puzzle Acc": "33.50",
|
| 82 |
+
"Total Puzzles": 1000,
|
| 83 |
+
"Reason Lens": "874.09",
|
| 84 |
+
"N_Mode": "single",
|
| 85 |
+
"N_Size": 1
|
| 86 |
+
},
|
| 87 |
{
|
| 88 |
"Model": "deepseek-R1",
|
| 89 |
"Mode": "greedy",
|