Spaces:
Running
Running
update results
Browse files
ZeroEval-main/result_dirs/zebra-grid.summary.json
CHANGED
|
@@ -285,6 +285,17 @@
|
|
| 285 |
"Total Puzzles": 1000,
|
| 286 |
"Reason Lens": "1216.40"
|
| 287 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 288 |
{
|
| 289 |
"Model": "Meta-Llama-3-8B-Instruct",
|
| 290 |
"Mode": "sampling",
|
|
@@ -318,6 +329,17 @@
|
|
| 318 |
"Total Puzzles": 1000,
|
| 319 |
"Reason Lens": "1074.80"
|
| 320 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 321 |
{
|
| 322 |
"Model": "Qwen2-7B-Instruct",
|
| 323 |
"Mode": "greedy",
|
|
@@ -328,5 +350,16 @@
|
|
| 328 |
"Hard Puzzle Acc": "0.28",
|
| 329 |
"Total Puzzles": 1000,
|
| 330 |
"Reason Lens": "1473.23"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 331 |
}
|
| 332 |
]
|
|
|
|
| 285 |
"Total Puzzles": 1000,
|
| 286 |
"Reason Lens": "1216.40"
|
| 287 |
},
|
| 288 |
+
{
|
| 289 |
+
"Model": "Yi-1.5-34B-Chat",
|
| 290 |
+
"Mode": "greedy",
|
| 291 |
+
"Puzzle Acc": "11.50",
|
| 292 |
+
"Cell Acc": "32.73",
|
| 293 |
+
"No answer": "4.40",
|
| 294 |
+
"Easy Puzzle Acc": "37.50",
|
| 295 |
+
"Hard Puzzle Acc": "1.39",
|
| 296 |
+
"Total Puzzles": 1000,
|
| 297 |
+
"Reason Lens": "869.65"
|
| 298 |
+
},
|
| 299 |
{
|
| 300 |
"Model": "Meta-Llama-3-8B-Instruct",
|
| 301 |
"Mode": "sampling",
|
|
|
|
| 329 |
"Total Puzzles": 1000,
|
| 330 |
"Reason Lens": "1074.80"
|
| 331 |
},
|
| 332 |
+
{
|
| 333 |
+
"Model": "mathstral-7B-v0.1",
|
| 334 |
+
"Mode": "greedy",
|
| 335 |
+
"Puzzle Acc": "9.00",
|
| 336 |
+
"Cell Acc": "20.42",
|
| 337 |
+
"No answer": "36.00",
|
| 338 |
+
"Easy Puzzle Acc": "30.00",
|
| 339 |
+
"Hard Puzzle Acc": "0.83",
|
| 340 |
+
"Total Puzzles": 1000,
|
| 341 |
+
"Reason Lens": "1148.16"
|
| 342 |
+
},
|
| 343 |
{
|
| 344 |
"Model": "Qwen2-7B-Instruct",
|
| 345 |
"Mode": "greedy",
|
|
|
|
| 350 |
"Hard Puzzle Acc": "0.28",
|
| 351 |
"Total Puzzles": 1000,
|
| 352 |
"Reason Lens": "1473.23"
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"Model": "Yi-1.5-9B-Chat",
|
| 356 |
+
"Mode": "greedy",
|
| 357 |
+
"Puzzle Acc": "2.30",
|
| 358 |
+
"Cell Acc": "7.53",
|
| 359 |
+
"No answer": "11.30",
|
| 360 |
+
"Easy Puzzle Acc": "8.21",
|
| 361 |
+
"Hard Puzzle Acc": "0.00",
|
| 362 |
+
"Total Puzzles": 1000,
|
| 363 |
+
"Reason Lens": "1592.60"
|
| 364 |
}
|
| 365 |
]
|