Spaces:
Sleeping
Sleeping
michal
commited on
Commit
·
c8fccfb
1
Parent(s):
bdc3484
Upload
Browse files- leaderboards/ldek_accs.json +297 -297
- leaderboards/lek_accs.json +264 -264
leaderboards/ldek_accs.json
CHANGED
|
@@ -1,93 +1,119 @@
|
|
| 1 |
[
|
| 2 |
{
|
| 3 |
-
"model_name": "model-
|
| 4 |
-
"2008 Fall
|
| 5 |
-
"2012 Spring":
|
| 6 |
-
"2010 Fall
|
| 7 |
-
"2009 Spring":
|
| 8 |
-
"2010 Spring":
|
| 9 |
-
"2011 Spring":
|
| 10 |
-
"2012 Fall
|
| 11 |
-
"2011 Fall
|
| 12 |
-
"2009 Fall
|
| 13 |
-
"2022 Spring":
|
| 14 |
-
"2014 Spring":
|
| 15 |
-
"2022 Fall":
|
| 16 |
-
"2014 Fall":
|
| 17 |
-
"2024 Spring":
|
| 18 |
-
"2015 Spring":
|
| 19 |
-
"2023 Spring":
|
| 20 |
-
"2021 Fall":
|
| 21 |
-
"2015 Fall":
|
| 22 |
-
"2023 Fall":
|
| 23 |
-
"2021 Spring":
|
| 24 |
-
"2013 Spring":
|
| 25 |
-
"2013 Fall":
|
| 26 |
-
"overall_accuracy":
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"model_name": "model-
|
| 30 |
-
"2008 Fall
|
| 31 |
-
"2012 Spring":
|
| 32 |
-
"2010 Fall
|
| 33 |
-
"2009 Spring":
|
| 34 |
-
"2010 Spring":
|
| 35 |
-
"2011 Spring":
|
| 36 |
-
"2012 Fall
|
| 37 |
-
"2011 Fall
|
| 38 |
-
"2009 Fall
|
| 39 |
-
"2022 Spring":
|
| 40 |
-
"2014 Spring":
|
| 41 |
-
"2022 Fall":
|
| 42 |
-
"2014 Fall":
|
| 43 |
-
"2024 Spring":
|
| 44 |
-
"2015 Spring":
|
| 45 |
-
"2023 Spring":
|
| 46 |
-
"2021 Fall":
|
| 47 |
-
"2015 Fall":
|
| 48 |
-
"2023 Fall":
|
| 49 |
-
"2021 Spring":
|
| 50 |
-
"2013 Spring":
|
| 51 |
-
"2013 Fall":
|
| 52 |
-
"overall_accuracy":
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"model_name": "model-
|
| 56 |
-
"2008 Fall
|
| 57 |
-
"2012 Spring":
|
| 58 |
-
"2010 Fall
|
| 59 |
-
"2009 Spring":
|
| 60 |
-
"2010 Spring":
|
| 61 |
-
"2011 Spring":
|
| 62 |
-
"2012 Fall
|
| 63 |
-
"2011 Fall
|
| 64 |
-
"2009 Fall
|
| 65 |
-
"2022 Spring":
|
| 66 |
-
"2014 Spring":
|
| 67 |
-
"2022 Fall":
|
| 68 |
-
"2014 Fall":
|
| 69 |
-
"2024 Spring":
|
| 70 |
-
"2015 Spring":
|
| 71 |
-
"2023 Spring":
|
| 72 |
-
"2021 Fall":
|
| 73 |
-
"2015 Fall":
|
| 74 |
-
"2023 Fall":
|
| 75 |
-
"2021 Spring":
|
| 76 |
-
"2013 Spring":
|
| 77 |
-
"2013 Fall":
|
| 78 |
-
"overall_accuracy":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"model_name": "model-gpt-4o-2024-08-06",
|
| 82 |
-
"2008 Fall
|
| 83 |
"2012 Spring": 77.83505154639175,
|
| 84 |
-
"2010 Fall
|
| 85 |
"2009 Spring": 85.85858585858585,
|
| 86 |
"2010 Spring": 83.0,
|
| 87 |
"2011 Spring": 72.22222222222221,
|
| 88 |
-
"2012 Fall
|
| 89 |
-
"2011 Fall
|
| 90 |
-
"2009 Fall
|
| 91 |
"2022 Spring": 77.27272727272727,
|
| 92 |
"2014 Spring": 79.08163265306123,
|
| 93 |
"2022 Fall": 69.38775510204081,
|
|
@@ -104,68 +130,94 @@
|
|
| 104 |
"overall_accuracy": 75.63239730796009
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"model_name": "model-
|
| 108 |
-
"2008 Fall
|
| 109 |
-
"2012 Spring":
|
| 110 |
-
"2010 Fall
|
| 111 |
-
"2009 Spring":
|
| 112 |
-
"2010 Spring":
|
| 113 |
"2011 Spring": 32.82828282828283,
|
| 114 |
-
"2012 Fall
|
| 115 |
-
"2011 Fall
|
| 116 |
-
"2009 Fall
|
| 117 |
-
"2022 Spring":
|
| 118 |
-
"2014 Spring":
|
| 119 |
-
"2022 Fall": 36.
|
| 120 |
-
"2014 Fall":
|
| 121 |
-
"2024 Spring":
|
| 122 |
"2015 Spring": 36.55913978494624,
|
| 123 |
-
"2023 Spring":
|
| 124 |
-
"2021 Fall":
|
| 125 |
-
"2015 Fall":
|
| 126 |
-
"2023 Fall":
|
| 127 |
-
"2021 Spring":
|
| 128 |
-
"2013 Spring":
|
| 129 |
-
"2013 Fall":
|
| 130 |
-
"overall_accuracy":
|
| 131 |
},
|
| 132 |
{
|
| 133 |
-
"model_name": "model-
|
| 134 |
-
"2008 Fall
|
| 135 |
-
"2012 Spring":
|
| 136 |
-
"2010 Fall
|
| 137 |
-
"2009 Spring":
|
| 138 |
-
"2010 Spring":
|
| 139 |
-
"2011 Spring":
|
| 140 |
-
"2012 Fall
|
| 141 |
-
"2011 Fall
|
| 142 |
-
"2009 Fall
|
| 143 |
-
"2022 Spring":
|
| 144 |
-
"2014 Spring":
|
| 145 |
"2022 Fall": 42.857142857142854,
|
| 146 |
-
"2014 Fall":
|
| 147 |
-
"2024 Spring":
|
| 148 |
-
"2015 Spring":
|
| 149 |
-
"2023 Spring":
|
| 150 |
-
"2021 Fall":
|
| 151 |
-
"2015 Fall":
|
| 152 |
-
"2023 Fall":
|
| 153 |
-
"2021 Spring":
|
| 154 |
-
"2013 Spring":
|
| 155 |
-
"2013 Fall":
|
| 156 |
-
"overall_accuracy":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"model_name": "model-gpt-4o-mini-2024-07-18",
|
| 160 |
-
"2008 Fall
|
| 161 |
"2012 Spring": 55.670103092783506,
|
| 162 |
-
"2010 Fall
|
| 163 |
"2009 Spring": 68.18181818181817,
|
| 164 |
"2010 Spring": 62.5,
|
| 165 |
"2011 Spring": 50.0,
|
| 166 |
-
"2012 Fall
|
| 167 |
-
"2011 Fall
|
| 168 |
-
"2009 Fall
|
| 169 |
"2022 Spring": 52.52525252525253,
|
| 170 |
"2014 Spring": 46.93877551020408,
|
| 171 |
"2022 Fall": 54.08163265306123,
|
|
@@ -183,15 +235,15 @@
|
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"model_name": "model-meta-llama-Llama-3.2-1B-Instruct",
|
| 186 |
-
"2008 Fall
|
| 187 |
"2012 Spring": 20.618556701030926,
|
| 188 |
-
"2010 Fall
|
| 189 |
"2009 Spring": 24.242424242424242,
|
| 190 |
"2010 Spring": 23.0,
|
| 191 |
"2011 Spring": 24.747474747474747,
|
| 192 |
-
"2012 Fall
|
| 193 |
-
"2011 Fall
|
| 194 |
-
"2009 Fall
|
| 195 |
"2022 Spring": 21.21212121212121,
|
| 196 |
"2014 Spring": 22.448979591836736,
|
| 197 |
"2022 Fall": 29.591836734693878,
|
|
@@ -208,68 +260,42 @@
|
|
| 208 |
"overall_accuracy": 25.08702715247157
|
| 209 |
},
|
| 210 |
{
|
| 211 |
-
"model_name": "model-
|
| 212 |
-
"2008 Fall
|
| 213 |
-
"2012 Spring":
|
| 214 |
-
"2010 Fall
|
| 215 |
-
"2009 Spring": 51.
|
| 216 |
-
"2010 Spring":
|
| 217 |
-
"2011 Spring":
|
| 218 |
-
"2012 Fall
|
| 219 |
-
"2011 Fall
|
| 220 |
-
"2009 Fall
|
| 221 |
-
"2022 Spring":
|
| 222 |
-
"2014 Spring":
|
| 223 |
-
"2022 Fall":
|
| 224 |
-
"2014 Fall":
|
| 225 |
-
"2024 Spring":
|
| 226 |
-
"2015 Spring":
|
| 227 |
-
"2023 Spring":
|
| 228 |
-
"2021 Fall":
|
| 229 |
-
"2015 Fall":
|
| 230 |
-
"2023 Fall":
|
| 231 |
-
"2021 Spring":
|
| 232 |
-
"2013 Spring":
|
| 233 |
-
"2013 Fall":
|
| 234 |
-
"overall_accuracy":
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"model_name": "model-meta-llama-Meta-Llama-3.1-8B-Instruct",
|
| 238 |
-
"2008 Falĺ": 40.4040404040404,
|
| 239 |
-
"2012 Spring": 40.72164948453608,
|
| 240 |
-
"2010 Falĺ": 43.71859296482412,
|
| 241 |
-
"2009 Spring": 47.97979797979798,
|
| 242 |
-
"2010 Spring": 46.0,
|
| 243 |
-
"2011 Spring": 33.83838383838384,
|
| 244 |
-
"2012 Falĺ": 50.0,
|
| 245 |
-
"2011 Falĺ": 41.41414141414141,
|
| 246 |
-
"2009 Falĺ": 54.0,
|
| 247 |
-
"2022 Spring": 38.88888888888889,
|
| 248 |
-
"2014 Spring": 33.16326530612245,
|
| 249 |
-
"2022 Fall": 40.816326530612244,
|
| 250 |
-
"2014 Fall": 42.487046632124354,
|
| 251 |
-
"2024 Spring": 39.59390862944163,
|
| 252 |
-
"2015 Spring": 42.473118279569896,
|
| 253 |
-
"2023 Spring": 44.94949494949495,
|
| 254 |
-
"2021 Fall": 40.909090909090914,
|
| 255 |
-
"2015 Fall": 41.578947368421055,
|
| 256 |
-
"2023 Fall": 42.05128205128205,
|
| 257 |
-
"2021 Spring": 41.3265306122449,
|
| 258 |
-
"2013 Spring": 41.23711340206185,
|
| 259 |
-
"2013 Fall": 44.50261780104712,
|
| 260 |
-
"overall_accuracy": 42.37642144349037
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"model_name": "model-aaditya-Llama3-OpenBioLLM-70B",
|
| 264 |
-
"2008 Fall
|
| 265 |
"2012 Spring": 19.072164948453608,
|
| 266 |
-
"2010 Fall
|
| 267 |
"2009 Spring": 50.0,
|
| 268 |
"2010 Spring": 43.0,
|
| 269 |
"2011 Spring": 38.88888888888889,
|
| 270 |
-
"2012 Fall
|
| 271 |
-
"2011 Fall
|
| 272 |
-
"2009 Fall
|
| 273 |
"2022 Spring": 45.95959595959596,
|
| 274 |
"2014 Spring": 39.285714285714285,
|
| 275 |
"2022 Fall": 43.36734693877551,
|
|
@@ -285,43 +311,17 @@
|
|
| 285 |
"2013 Fall": 42.93193717277487,
|
| 286 |
"overall_accuracy": 39.777210489672775
|
| 287 |
},
|
| 288 |
-
{
|
| 289 |
-
"model_name": "model-Qwen-Qwen2.5-7B-Instruct",
|
| 290 |
-
"2008 Falĺ": 41.41414141414141,
|
| 291 |
-
"2012 Spring": 40.20618556701031,
|
| 292 |
-
"2010 Falĺ": 43.21608040201005,
|
| 293 |
-
"2009 Spring": 40.4040404040404,
|
| 294 |
-
"2010 Spring": 41.5,
|
| 295 |
-
"2011 Spring": 38.38383838383838,
|
| 296 |
-
"2012 Falĺ": 48.97959183673469,
|
| 297 |
-
"2011 Falĺ": 38.88888888888889,
|
| 298 |
-
"2009 Falĺ": 43.5,
|
| 299 |
-
"2022 Spring": 43.93939393939394,
|
| 300 |
-
"2014 Spring": 35.714285714285715,
|
| 301 |
-
"2022 Fall": 42.857142857142854,
|
| 302 |
-
"2014 Fall": 46.63212435233161,
|
| 303 |
-
"2024 Spring": 45.68527918781726,
|
| 304 |
-
"2015 Spring": 42.473118279569896,
|
| 305 |
-
"2023 Spring": 44.94949494949495,
|
| 306 |
-
"2021 Fall": 43.43434343434344,
|
| 307 |
-
"2015 Fall": 40.0,
|
| 308 |
-
"2023 Fall": 46.15384615384615,
|
| 309 |
-
"2021 Spring": 47.44897959183674,
|
| 310 |
-
"2013 Spring": 44.84536082474227,
|
| 311 |
-
"2013 Fall": 43.97905759162304,
|
| 312 |
-
"overall_accuracy": 42.93339521930842
|
| 313 |
-
},
|
| 314 |
{
|
| 315 |
"model_name": "model-meta-llama-Meta-Llama-3.1-70B-Instruct",
|
| 316 |
-
"2008 Fall
|
| 317 |
"2012 Spring": 61.34020618556701,
|
| 318 |
-
"2010 Fall
|
| 319 |
"2009 Spring": 69.1919191919192,
|
| 320 |
"2010 Spring": 73.0,
|
| 321 |
"2011 Spring": 59.59595959595959,
|
| 322 |
-
"2012 Fall
|
| 323 |
-
"2011 Fall
|
| 324 |
-
"2009 Fall
|
| 325 |
"2022 Spring": 68.68686868686868,
|
| 326 |
"2014 Spring": 54.59183673469388,
|
| 327 |
"2022 Fall": 62.755102040816325,
|
|
@@ -338,68 +338,42 @@
|
|
| 338 |
"overall_accuracy": 63.402181480621955
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"model_name": "model-
|
| 342 |
-
"2008 Fall
|
| 343 |
-
"2012 Spring":
|
| 344 |
-
"2010 Fall
|
| 345 |
-
"2009 Spring":
|
| 346 |
-
"2010 Spring":
|
| 347 |
-
"2011 Spring":
|
| 348 |
-
"2012 Fall
|
| 349 |
-
"2011 Fall
|
| 350 |
-
"2009 Fall
|
| 351 |
-
"2022 Spring":
|
| 352 |
-
"2014 Spring":
|
| 353 |
-
"2022 Fall":
|
| 354 |
-
"2014 Fall":
|
| 355 |
-
"2024 Spring":
|
| 356 |
-
"2015 Spring":
|
| 357 |
-
"2023 Spring":
|
| 358 |
-
"2021 Fall":
|
| 359 |
-
"2015 Fall":
|
| 360 |
-
"2023 Fall":
|
| 361 |
-
"2021 Spring":
|
| 362 |
-
"2013 Spring":
|
| 363 |
-
"2013 Fall":
|
| 364 |
-
"overall_accuracy":
|
| 365 |
-
},
|
| 366 |
-
{
|
| 367 |
-
"model_name": "model-BioMistral-BioMistral-7B",
|
| 368 |
-
"2008 Falĺ": 23.232323232323232,
|
| 369 |
-
"2012 Spring": 21.1340206185567,
|
| 370 |
-
"2010 Falĺ": 23.115577889447238,
|
| 371 |
-
"2009 Spring": 25.757575757575758,
|
| 372 |
-
"2010 Spring": 23.0,
|
| 373 |
-
"2011 Spring": 23.737373737373737,
|
| 374 |
-
"2012 Falĺ": 28.57142857142857,
|
| 375 |
-
"2011 Falĺ": 24.242424242424242,
|
| 376 |
-
"2009 Falĺ": 23.5,
|
| 377 |
-
"2022 Spring": 20.2020202020202,
|
| 378 |
-
"2014 Spring": 24.489795918367346,
|
| 379 |
-
"2022 Fall": 28.57142857142857,
|
| 380 |
-
"2014 Fall": 22.279792746113987,
|
| 381 |
-
"2024 Spring": 25.888324873096447,
|
| 382 |
-
"2015 Spring": 24.731182795698924,
|
| 383 |
-
"2023 Spring": 24.747474747474747,
|
| 384 |
-
"2021 Fall": 26.767676767676768,
|
| 385 |
-
"2015 Fall": 28.421052631578945,
|
| 386 |
-
"2023 Fall": 25.64102564102564,
|
| 387 |
-
"2021 Spring": 19.387755102040817,
|
| 388 |
-
"2013 Spring": 23.711340206185564,
|
| 389 |
-
"2013 Fall": 29.84293193717277,
|
| 390 |
-
"overall_accuracy": 24.576467857971686
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"model_name": "model-ProbeMedicalYonseiMAILab-medllama3-v20",
|
| 394 |
-
"2008 Fall
|
| 395 |
"2012 Spring": 31.958762886597935,
|
| 396 |
-
"2010 Fall
|
| 397 |
"2009 Spring": 37.37373737373738,
|
| 398 |
"2010 Spring": 31.5,
|
| 399 |
"2011 Spring": 30.808080808080806,
|
| 400 |
-
"2012 Fall
|
| 401 |
-
"2011 Fall
|
| 402 |
-
"2009 Fall
|
| 403 |
"2022 Spring": 34.84848484848485,
|
| 404 |
"2014 Spring": 26.53061224489796,
|
| 405 |
"2022 Fall": 34.183673469387756,
|
|
@@ -416,29 +390,55 @@
|
|
| 416 |
"overall_accuracy": 34.04502204687863
|
| 417 |
},
|
| 418 |
{
|
| 419 |
-
"model_name": "model-
|
| 420 |
-
"2008 Fall
|
| 421 |
-
"2012 Spring":
|
| 422 |
-
"2010 Fall
|
| 423 |
-
"2009 Spring":
|
| 424 |
-
"2010 Spring":
|
| 425 |
-
"2011 Spring":
|
| 426 |
-
"2012 Fall
|
| 427 |
-
"2011 Fall
|
| 428 |
-
"2009 Fall
|
| 429 |
-
"2022 Spring":
|
| 430 |
-
"2014 Spring":
|
| 431 |
-
"2022 Fall":
|
| 432 |
-
"2014 Fall":
|
| 433 |
-
"2024 Spring":
|
| 434 |
-
"2015 Spring":
|
| 435 |
-
"2023 Spring":
|
| 436 |
-
"2021 Fall":
|
| 437 |
-
"2015 Fall":
|
| 438 |
-
"2023 Fall":
|
| 439 |
-
"2021 Spring":
|
| 440 |
-
"2013 Spring":
|
| 441 |
-
"2013 Fall":
|
| 442 |
-
"overall_accuracy":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 443 |
}
|
| 444 |
]
|
|
|
|
| 1 |
[
|
| 2 |
{
|
| 3 |
+
"model_name": "model-BioMistral-BioMistral-7B",
|
| 4 |
+
"2008 Fall": 23.232323232323232,
|
| 5 |
+
"2012 Spring": 21.1340206185567,
|
| 6 |
+
"2010 Fall": 23.115577889447238,
|
| 7 |
+
"2009 Spring": 25.757575757575758,
|
| 8 |
+
"2010 Spring": 23.0,
|
| 9 |
+
"2011 Spring": 23.737373737373737,
|
| 10 |
+
"2012 Fall": 28.57142857142857,
|
| 11 |
+
"2011 Fall": 24.242424242424242,
|
| 12 |
+
"2009 Fall": 23.5,
|
| 13 |
+
"2022 Spring": 20.2020202020202,
|
| 14 |
+
"2014 Spring": 24.489795918367346,
|
| 15 |
+
"2022 Fall": 28.57142857142857,
|
| 16 |
+
"2014 Fall": 22.279792746113987,
|
| 17 |
+
"2024 Spring": 25.888324873096447,
|
| 18 |
+
"2015 Spring": 24.731182795698924,
|
| 19 |
+
"2023 Spring": 24.747474747474747,
|
| 20 |
+
"2021 Fall": 26.767676767676768,
|
| 21 |
+
"2015 Fall": 28.421052631578945,
|
| 22 |
+
"2023 Fall": 25.64102564102564,
|
| 23 |
+
"2021 Spring": 19.387755102040817,
|
| 24 |
+
"2013 Spring": 23.711340206185564,
|
| 25 |
+
"2013 Fall": 29.84293193717277,
|
| 26 |
+
"overall_accuracy": 24.576467857971686
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"model_name": "model-johnsnowlabs-JSL-MedLlama-3-8B-v2.0",
|
| 30 |
+
"2008 Fall": 29.292929292929294,
|
| 31 |
+
"2012 Spring": 31.958762886597935,
|
| 32 |
+
"2010 Fall": 28.14070351758794,
|
| 33 |
+
"2009 Spring": 31.313131313131315,
|
| 34 |
+
"2010 Spring": 35.0,
|
| 35 |
+
"2011 Spring": 23.737373737373737,
|
| 36 |
+
"2012 Fall": 38.265306122448976,
|
| 37 |
+
"2011 Fall": 25.757575757575758,
|
| 38 |
+
"2009 Fall": 35.0,
|
| 39 |
+
"2022 Spring": 30.808080808080806,
|
| 40 |
+
"2014 Spring": 31.122448979591837,
|
| 41 |
+
"2022 Fall": 34.69387755102041,
|
| 42 |
+
"2014 Fall": 34.196891191709845,
|
| 43 |
+
"2024 Spring": 29.949238578680205,
|
| 44 |
+
"2015 Spring": 31.182795698924732,
|
| 45 |
+
"2023 Spring": 30.808080808080806,
|
| 46 |
+
"2021 Fall": 29.797979797979796,
|
| 47 |
+
"2015 Fall": 26.31578947368421,
|
| 48 |
+
"2023 Fall": 32.82051282051282,
|
| 49 |
+
"2021 Spring": 33.6734693877551,
|
| 50 |
+
"2013 Spring": 30.927835051546392,
|
| 51 |
+
"2013 Fall": 30.89005235602094,
|
| 52 |
+
"overall_accuracy": 31.16732420515201
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"model_name": "model-meta-llama-Meta-Llama-3.1-8B-Instruct",
|
| 56 |
+
"2008 Fall": 40.4040404040404,
|
| 57 |
+
"2012 Spring": 40.72164948453608,
|
| 58 |
+
"2010 Fall": 43.71859296482412,
|
| 59 |
+
"2009 Spring": 47.97979797979798,
|
| 60 |
+
"2010 Spring": 46.0,
|
| 61 |
+
"2011 Spring": 33.83838383838384,
|
| 62 |
+
"2012 Fall": 50.0,
|
| 63 |
+
"2011 Fall": 41.41414141414141,
|
| 64 |
+
"2009 Fall": 54.0,
|
| 65 |
+
"2022 Spring": 38.88888888888889,
|
| 66 |
+
"2014 Spring": 33.16326530612245,
|
| 67 |
+
"2022 Fall": 40.816326530612244,
|
| 68 |
+
"2014 Fall": 42.487046632124354,
|
| 69 |
+
"2024 Spring": 39.59390862944163,
|
| 70 |
+
"2015 Spring": 42.473118279569896,
|
| 71 |
+
"2023 Spring": 44.94949494949495,
|
| 72 |
+
"2021 Fall": 40.909090909090914,
|
| 73 |
+
"2015 Fall": 41.578947368421055,
|
| 74 |
+
"2023 Fall": 42.05128205128205,
|
| 75 |
+
"2021 Spring": 41.3265306122449,
|
| 76 |
+
"2013 Spring": 41.23711340206185,
|
| 77 |
+
"2013 Fall": 44.50261780104712,
|
| 78 |
+
"overall_accuracy": 42.37642144349037
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"model_name": "model-speakleash-Bielik-11B-v2.2-Instruct",
|
| 82 |
+
"2008 Fall": 45.45454545454545,
|
| 83 |
+
"2012 Spring": 46.391752577319586,
|
| 84 |
+
"2010 Fall": 52.26130653266332,
|
| 85 |
+
"2009 Spring": 51.515151515151516,
|
| 86 |
+
"2010 Spring": 48.5,
|
| 87 |
+
"2011 Spring": 41.91919191919192,
|
| 88 |
+
"2012 Fall": 57.6530612244898,
|
| 89 |
+
"2011 Fall": 45.95959595959596,
|
| 90 |
+
"2009 Fall": 49.5,
|
| 91 |
+
"2022 Spring": 40.4040404040404,
|
| 92 |
+
"2014 Spring": 34.69387755102041,
|
| 93 |
+
"2022 Fall": 43.36734693877551,
|
| 94 |
+
"2014 Fall": 44.04145077720207,
|
| 95 |
+
"2024 Spring": 50.76142131979695,
|
| 96 |
+
"2015 Spring": 43.54838709677419,
|
| 97 |
+
"2023 Spring": 41.91919191919192,
|
| 98 |
+
"2021 Fall": 43.93939393939394,
|
| 99 |
+
"2015 Fall": 40.0,
|
| 100 |
+
"2023 Fall": 37.94871794871795,
|
| 101 |
+
"2021 Spring": 50.0,
|
| 102 |
+
"2013 Spring": 47.93814432989691,
|
| 103 |
+
"2013 Fall": 42.93193717277487,
|
| 104 |
+
"overall_accuracy": 45.50939893246693
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"model_name": "model-gpt-4o-2024-08-06",
|
| 108 |
+
"2008 Fall": 78.78787878787878,
|
| 109 |
"2012 Spring": 77.83505154639175,
|
| 110 |
+
"2010 Fall": 74.37185929648241,
|
| 111 |
"2009 Spring": 85.85858585858585,
|
| 112 |
"2010 Spring": 83.0,
|
| 113 |
"2011 Spring": 72.22222222222221,
|
| 114 |
+
"2012 Fall": 76.53061224489795,
|
| 115 |
+
"2011 Fall": 72.72727272727273,
|
| 116 |
+
"2009 Fall": 81.5,
|
| 117 |
"2022 Spring": 77.27272727272727,
|
| 118 |
"2014 Spring": 79.08163265306123,
|
| 119 |
"2022 Fall": 69.38775510204081,
|
|
|
|
| 130 |
"overall_accuracy": 75.63239730796009
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"model_name": "model-OpenMeditron-Meditron3-8B",
|
| 134 |
+
"2008 Fall": 38.88888888888889,
|
| 135 |
+
"2012 Spring": 39.69072164948454,
|
| 136 |
+
"2010 Fall": 36.18090452261307,
|
| 137 |
+
"2009 Spring": 41.41414141414141,
|
| 138 |
+
"2010 Spring": 43.0,
|
| 139 |
"2011 Spring": 32.82828282828283,
|
| 140 |
+
"2012 Fall": 42.3469387755102,
|
| 141 |
+
"2011 Fall": 33.33333333333333,
|
| 142 |
+
"2009 Fall": 41.5,
|
| 143 |
+
"2022 Spring": 34.34343434343434,
|
| 144 |
+
"2014 Spring": 30.102040816326532,
|
| 145 |
+
"2022 Fall": 36.734693877551024,
|
| 146 |
+
"2014 Fall": 39.89637305699482,
|
| 147 |
+
"2024 Spring": 38.07106598984771,
|
| 148 |
"2015 Spring": 36.55913978494624,
|
| 149 |
+
"2023 Spring": 38.38383838383838,
|
| 150 |
+
"2021 Fall": 41.41414141414141,
|
| 151 |
+
"2015 Fall": 39.473684210526315,
|
| 152 |
+
"2023 Fall": 34.35897435897436,
|
| 153 |
+
"2021 Spring": 40.816326530612244,
|
| 154 |
+
"2013 Spring": 42.78350515463917,
|
| 155 |
+
"2013 Fall": 40.83769633507853,
|
| 156 |
+
"overall_accuracy": 38.31515432815038
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"model_name": "model-Qwen-Qwen2.5-7B-Instruct",
|
| 160 |
+
"2008 Fall": 41.41414141414141,
|
| 161 |
+
"2012 Spring": 40.20618556701031,
|
| 162 |
+
"2010 Fall": 43.21608040201005,
|
| 163 |
+
"2009 Spring": 40.4040404040404,
|
| 164 |
+
"2010 Spring": 41.5,
|
| 165 |
+
"2011 Spring": 38.38383838383838,
|
| 166 |
+
"2012 Fall": 48.97959183673469,
|
| 167 |
+
"2011 Fall": 38.88888888888889,
|
| 168 |
+
"2009 Fall": 43.5,
|
| 169 |
+
"2022 Spring": 43.93939393939394,
|
| 170 |
+
"2014 Spring": 35.714285714285715,
|
| 171 |
"2022 Fall": 42.857142857142854,
|
| 172 |
+
"2014 Fall": 46.63212435233161,
|
| 173 |
+
"2024 Spring": 45.68527918781726,
|
| 174 |
+
"2015 Spring": 42.473118279569896,
|
| 175 |
+
"2023 Spring": 44.94949494949495,
|
| 176 |
+
"2021 Fall": 43.43434343434344,
|
| 177 |
+
"2015 Fall": 40.0,
|
| 178 |
+
"2023 Fall": 46.15384615384615,
|
| 179 |
+
"2021 Spring": 47.44897959183674,
|
| 180 |
+
"2013 Spring": 44.84536082474227,
|
| 181 |
+
"2013 Fall": 43.97905759162304,
|
| 182 |
+
"overall_accuracy": 42.93339521930842
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"model_name": "model-mistralai-Mistral-Large-Instruct-2407",
|
| 186 |
+
"2008 Fall": 61.61616161616161,
|
| 187 |
+
"2012 Spring": 54.123711340206185,
|
| 188 |
+
"2010 Fall": 62.311557788944725,
|
| 189 |
+
"2009 Spring": 67.67676767676768,
|
| 190 |
+
"2010 Spring": 69.5,
|
| 191 |
+
"2011 Spring": 56.56565656565656,
|
| 192 |
+
"2012 Fall": 66.3265306122449,
|
| 193 |
+
"2011 Fall": 58.080808080808076,
|
| 194 |
+
"2009 Fall": 63.0,
|
| 195 |
+
"2022 Spring": 54.54545454545454,
|
| 196 |
+
"2014 Spring": 54.08163265306123,
|
| 197 |
+
"2022 Fall": 56.63265306122449,
|
| 198 |
+
"2014 Fall": 56.476683937823836,
|
| 199 |
+
"2024 Spring": 55.83756345177665,
|
| 200 |
+
"2015 Spring": 58.602150537634415,
|
| 201 |
+
"2023 Spring": 57.57575757575758,
|
| 202 |
+
"2021 Fall": 56.060606060606055,
|
| 203 |
+
"2015 Fall": 60.0,
|
| 204 |
+
"2023 Fall": 48.205128205128204,
|
| 205 |
+
"2021 Spring": 57.14285714285714,
|
| 206 |
+
"2013 Spring": 61.34020618556701,
|
| 207 |
+
"2013 Fall": 55.497382198952884,
|
| 208 |
+
"overall_accuracy": 58.71431886748666
|
| 209 |
},
|
| 210 |
{
|
| 211 |
"model_name": "model-gpt-4o-mini-2024-07-18",
|
| 212 |
+
"2008 Fall": 59.09090909090909,
|
| 213 |
"2012 Spring": 55.670103092783506,
|
| 214 |
+
"2010 Fall": 55.27638190954774,
|
| 215 |
"2009 Spring": 68.18181818181817,
|
| 216 |
"2010 Spring": 62.5,
|
| 217 |
"2011 Spring": 50.0,
|
| 218 |
+
"2012 Fall": 65.3061224489796,
|
| 219 |
+
"2011 Fall": 55.05050505050505,
|
| 220 |
+
"2009 Fall": 64.0,
|
| 221 |
"2022 Spring": 52.52525252525253,
|
| 222 |
"2014 Spring": 46.93877551020408,
|
| 223 |
"2022 Fall": 54.08163265306123,
|
|
|
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"model_name": "model-meta-llama-Llama-3.2-1B-Instruct",
|
| 238 |
+
"2008 Fall": 24.242424242424242,
|
| 239 |
"2012 Spring": 20.618556701030926,
|
| 240 |
+
"2010 Fall": 23.618090452261306,
|
| 241 |
"2009 Spring": 24.242424242424242,
|
| 242 |
"2010 Spring": 23.0,
|
| 243 |
"2011 Spring": 24.747474747474747,
|
| 244 |
+
"2012 Fall": 28.57142857142857,
|
| 245 |
+
"2011 Fall": 21.71717171717172,
|
| 246 |
+
"2009 Fall": 25.5,
|
| 247 |
"2022 Spring": 21.21212121212121,
|
| 248 |
"2014 Spring": 22.448979591836736,
|
| 249 |
"2022 Fall": 29.591836734693878,
|
|
|
|
| 260 |
"overall_accuracy": 25.08702715247157
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"model_name": "model-OpenMeditron-Meditron3-70B",
|
| 264 |
+
"2008 Fall": 45.95959595959596,
|
| 265 |
+
"2012 Spring": 43.29896907216495,
|
| 266 |
+
"2010 Fall": 46.733668341708544,
|
| 267 |
+
"2009 Spring": 51.010101010101,
|
| 268 |
+
"2010 Spring": 49.0,
|
| 269 |
+
"2011 Spring": 42.42424242424242,
|
| 270 |
+
"2012 Fall": 47.44897959183674,
|
| 271 |
+
"2011 Fall": 46.96969696969697,
|
| 272 |
+
"2009 Fall": 49.0,
|
| 273 |
+
"2022 Spring": 45.95959595959596,
|
| 274 |
+
"2014 Spring": 41.83673469387755,
|
| 275 |
+
"2022 Fall": 48.46938775510204,
|
| 276 |
+
"2014 Fall": 47.15025906735752,
|
| 277 |
+
"2024 Spring": 52.28426395939086,
|
| 278 |
+
"2015 Spring": 50.53763440860215,
|
| 279 |
+
"2023 Spring": 47.474747474747474,
|
| 280 |
+
"2021 Fall": 48.98989898989899,
|
| 281 |
+
"2015 Fall": 51.05263157894737,
|
| 282 |
+
"2023 Fall": 42.56410256410256,
|
| 283 |
+
"2021 Spring": 45.40816326530612,
|
| 284 |
+
"2013 Spring": 49.48453608247423,
|
| 285 |
+
"2013 Fall": 45.54973821989529,
|
| 286 |
+
"overall_accuracy": 47.203527500580186
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"model_name": "model-aaditya-Llama3-OpenBioLLM-70B",
|
| 290 |
+
"2008 Fall": 19.19191919191919,
|
| 291 |
"2012 Spring": 19.072164948453608,
|
| 292 |
+
"2010 Fall": 35.175879396984925,
|
| 293 |
"2009 Spring": 50.0,
|
| 294 |
"2010 Spring": 43.0,
|
| 295 |
"2011 Spring": 38.88888888888889,
|
| 296 |
+
"2012 Fall": 43.36734693877551,
|
| 297 |
+
"2011 Fall": 35.35353535353536,
|
| 298 |
+
"2009 Fall": 48.0,
|
| 299 |
"2022 Spring": 45.95959595959596,
|
| 300 |
"2014 Spring": 39.285714285714285,
|
| 301 |
"2022 Fall": 43.36734693877551,
|
|
|
|
| 311 |
"2013 Fall": 42.93193717277487,
|
| 312 |
"overall_accuracy": 39.777210489672775
|
| 313 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 314 |
{
|
| 315 |
"model_name": "model-meta-llama-Meta-Llama-3.1-70B-Instruct",
|
| 316 |
+
"2008 Fall": 62.121212121212125,
|
| 317 |
"2012 Spring": 61.34020618556701,
|
| 318 |
+
"2010 Fall": 62.8140703517588,
|
| 319 |
"2009 Spring": 69.1919191919192,
|
| 320 |
"2010 Spring": 73.0,
|
| 321 |
"2011 Spring": 59.59595959595959,
|
| 322 |
+
"2012 Fall": 69.89795918367348,
|
| 323 |
+
"2011 Fall": 65.65656565656566,
|
| 324 |
+
"2009 Fall": 68.0,
|
| 325 |
"2022 Spring": 68.68686868686868,
|
| 326 |
"2014 Spring": 54.59183673469388,
|
| 327 |
"2022 Fall": 62.755102040816325,
|
|
|
|
| 338 |
"overall_accuracy": 63.402181480621955
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"model_name": "model-meta-llama-Llama-3.2-3B-Instruct",
|
| 342 |
+
"2008 Fall": 36.36363636363637,
|
| 343 |
+
"2012 Spring": 30.927835051546392,
|
| 344 |
+
"2010 Fall": 36.18090452261307,
|
| 345 |
+
"2009 Spring": 34.34343434343434,
|
| 346 |
+
"2010 Spring": 40.5,
|
| 347 |
+
"2011 Spring": 32.82828282828283,
|
| 348 |
+
"2012 Fall": 40.816326530612244,
|
| 349 |
+
"2011 Fall": 29.292929292929294,
|
| 350 |
+
"2009 Fall": 43.0,
|
| 351 |
+
"2022 Spring": 29.797979797979796,
|
| 352 |
+
"2014 Spring": 28.061224489795915,
|
| 353 |
+
"2022 Fall": 36.224489795918366,
|
| 354 |
+
"2014 Fall": 29.533678756476682,
|
| 355 |
+
"2024 Spring": 35.53299492385787,
|
| 356 |
+
"2015 Spring": 36.55913978494624,
|
| 357 |
+
"2023 Spring": 35.35353535353536,
|
| 358 |
+
"2021 Fall": 27.77777777777778,
|
| 359 |
+
"2015 Fall": 30.526315789473685,
|
| 360 |
+
"2023 Fall": 29.230769230769234,
|
| 361 |
+
"2021 Spring": 31.122448979591837,
|
| 362 |
+
"2013 Spring": 33.50515463917525,
|
| 363 |
+
"2013 Fall": 35.07853403141361,
|
| 364 |
+
"overall_accuracy": 33.766535158969596
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"model_name": "model-ProbeMedicalYonseiMAILab-medllama3-v20",
|
| 368 |
+
"2008 Fall": 30.303030303030305,
|
| 369 |
"2012 Spring": 31.958762886597935,
|
| 370 |
+
"2010 Fall": 30.15075376884422,
|
| 371 |
"2009 Spring": 37.37373737373738,
|
| 372 |
"2010 Spring": 31.5,
|
| 373 |
"2011 Spring": 30.808080808080806,
|
| 374 |
+
"2012 Fall": 34.69387755102041,
|
| 375 |
+
"2011 Fall": 30.808080808080806,
|
| 376 |
+
"2009 Fall": 35.5,
|
| 377 |
"2022 Spring": 34.84848484848485,
|
| 378 |
"2014 Spring": 26.53061224489796,
|
| 379 |
"2022 Fall": 34.183673469387756,
|
|
|
|
| 390 |
"overall_accuracy": 34.04502204687863
|
| 391 |
},
|
| 392 |
{
|
| 393 |
+
"model_name": "model-mistralai-Mistral-Small-Instruct-2409",
|
| 394 |
+
"2008 Fall": 38.38383838383838,
|
| 395 |
+
"2012 Spring": 34.5360824742268,
|
| 396 |
+
"2010 Fall": 40.7035175879397,
|
| 397 |
+
"2009 Spring": 44.44444444444444,
|
| 398 |
+
"2010 Spring": 46.5,
|
| 399 |
+
"2011 Spring": 34.84848484848485,
|
| 400 |
+
"2012 Fall": 46.42857142857143,
|
| 401 |
+
"2011 Fall": 38.88888888888889,
|
| 402 |
+
"2009 Fall": 45.0,
|
| 403 |
+
"2022 Spring": 38.88888888888889,
|
| 404 |
+
"2014 Spring": 34.69387755102041,
|
| 405 |
+
"2022 Fall": 42.857142857142854,
|
| 406 |
+
"2014 Fall": 37.82383419689119,
|
| 407 |
+
"2024 Spring": 44.16243654822335,
|
| 408 |
+
"2015 Spring": 38.17204301075269,
|
| 409 |
+
"2023 Spring": 41.41414141414141,
|
| 410 |
+
"2021 Fall": 42.42424242424242,
|
| 411 |
+
"2015 Fall": 42.10526315789473,
|
| 412 |
+
"2023 Fall": 40.0,
|
| 413 |
+
"2021 Spring": 41.3265306122449,
|
| 414 |
+
"2013 Spring": 43.29896907216495,
|
| 415 |
+
"2013 Fall": 44.50261780104712,
|
| 416 |
+
"overall_accuracy": 40.98398700394523
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"model_name": "model-Qwen-Qwen2.5-72B-Instruct",
|
| 420 |
+
"2008 Fall": 58.58585858585859,
|
| 421 |
+
"2012 Spring": 56.70103092783505,
|
| 422 |
+
"2010 Fall": 60.80402010050251,
|
| 423 |
+
"2009 Spring": 60.1010101010101,
|
| 424 |
+
"2010 Spring": 63.5,
|
| 425 |
+
"2011 Spring": 58.58585858585859,
|
| 426 |
+
"2012 Fall": 66.83673469387756,
|
| 427 |
+
"2011 Fall": 54.54545454545454,
|
| 428 |
+
"2009 Fall": 70.5,
|
| 429 |
+
"2022 Spring": 59.59595959595959,
|
| 430 |
+
"2014 Spring": 53.57142857142857,
|
| 431 |
+
"2022 Fall": 61.73469387755102,
|
| 432 |
+
"2014 Fall": 61.6580310880829,
|
| 433 |
+
"2024 Spring": 57.360406091370564,
|
| 434 |
+
"2015 Spring": 58.602150537634415,
|
| 435 |
+
"2023 Spring": 56.56565656565656,
|
| 436 |
+
"2021 Fall": 59.59595959595959,
|
| 437 |
+
"2015 Fall": 57.36842105263158,
|
| 438 |
+
"2023 Fall": 54.871794871794876,
|
| 439 |
+
"2021 Spring": 58.673469387755105,
|
| 440 |
+
"2013 Spring": 61.855670103092784,
|
| 441 |
+
"2013 Fall": 57.06806282722513,
|
| 442 |
+
"overall_accuracy": 59.503365049895564
|
| 443 |
}
|
| 444 |
]
|
leaderboards/lek_accs.json
CHANGED
|
@@ -1,41 +1,119 @@
|
|
| 1 |
[
|
| 2 |
{
|
| 3 |
-
"model_name": "model-
|
| 4 |
-
"2011 Spring":
|
| 5 |
-
"2010 Spring":
|
| 6 |
-
"2008 Fall
|
| 7 |
-
"2011 Fall
|
| 8 |
-
"2009 Fall
|
| 9 |
-
"2010 Fall
|
| 10 |
-
"2012 Spring":
|
| 11 |
-
"2009 Spring":
|
| 12 |
-
"2012 Fall
|
| 13 |
-
"2022 Spring":
|
| 14 |
-
"2014 Spring":
|
| 15 |
-
"2022 Fall":
|
| 16 |
-
"2014 Fall":
|
| 17 |
-
"2024 Spring":
|
| 18 |
-
"2015 Spring":
|
| 19 |
-
"2023 Spring":
|
| 20 |
-
"2021 Fall":
|
| 21 |
-
"2015 Fall":
|
| 22 |
-
"2023 Fall":
|
| 23 |
-
"2021 Spring":
|
| 24 |
-
"2013 Spring":
|
| 25 |
-
"2013 Fall":
|
| 26 |
-
"overall_accuracy":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"model_name": "model-gpt-4o-2024-08-06",
|
| 30 |
"2011 Spring": 87.37373737373737,
|
| 31 |
"2010 Spring": 88.5,
|
| 32 |
-
"2008 Fall
|
| 33 |
-
"2011 Fall
|
| 34 |
-
"2009 Fall
|
| 35 |
-
"2010 Fall
|
| 36 |
"2012 Spring": 90.0,
|
| 37 |
"2009 Spring": 86.93467336683418,
|
| 38 |
-
"2012 Fall
|
| 39 |
"2022 Spring": 89.28571428571429,
|
| 40 |
"2014 Spring": 88.71794871794872,
|
| 41 |
"2022 Fall": 91.3265306122449,
|
|
@@ -52,42 +130,42 @@
|
|
| 52 |
"overall_accuracy": 89.40166975881262
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"model_name": "model-
|
| 56 |
-
"2011 Spring":
|
| 57 |
-
"2010 Spring":
|
| 58 |
-
"2008 Fall
|
| 59 |
-
"2011 Fall
|
| 60 |
-
"2009 Fall
|
| 61 |
-
"2010 Fall
|
| 62 |
-
"2012 Spring":
|
| 63 |
-
"2009 Spring":
|
| 64 |
-
"2012 Fall
|
| 65 |
-
"2022 Spring":
|
| 66 |
-
"2014 Spring":
|
| 67 |
-
"2022 Fall":
|
| 68 |
-
"2014 Fall":
|
| 69 |
-
"2024 Spring":
|
| 70 |
-
"2015 Spring":
|
| 71 |
-
"2023 Spring":
|
| 72 |
-
"2021 Fall":
|
| 73 |
-
"2015 Fall":
|
| 74 |
-
"2023 Fall":
|
| 75 |
-
"2021 Spring":
|
| 76 |
-
"2013 Spring":
|
| 77 |
-
"2013 Fall":
|
| 78 |
-
"overall_accuracy":
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"model_name": "model-OpenMeditron-Meditron3-8B",
|
| 82 |
"2011 Spring": 43.93939393939394,
|
| 83 |
"2010 Spring": 48.0,
|
| 84 |
-
"2008 Fall
|
| 85 |
-
"2011 Fall
|
| 86 |
-
"2009 Fall
|
| 87 |
-
"2010 Fall
|
| 88 |
"2012 Spring": 43.5,
|
| 89 |
"2009 Spring": 43.21608040201005,
|
| 90 |
-
"2012 Fall
|
| 91 |
"2022 Spring": 41.83673469387755,
|
| 92 |
"2014 Spring": 42.05128205128205,
|
| 93 |
"2022 Fall": 43.36734693877551,
|
|
@@ -103,43 +181,17 @@
|
|
| 103 |
"2013 Fall": 51.832460732984295,
|
| 104 |
"overall_accuracy": 45.570500927643785
|
| 105 |
},
|
| 106 |
-
{
|
| 107 |
-
"model_name": "model-meta-llama-Llama-3.2-3B-Instruct",
|
| 108 |
-
"2011 Spring": 36.868686868686865,
|
| 109 |
-
"2010 Spring": 38.0,
|
| 110 |
-
"2008 Falĺ": 38.578680203045685,
|
| 111 |
-
"2011 Falĺ": 47.97979797979798,
|
| 112 |
-
"2009 Falĺ": 38.578680203045685,
|
| 113 |
-
"2010 Falĺ": 38.38383838383838,
|
| 114 |
-
"2012 Spring": 36.0,
|
| 115 |
-
"2009 Spring": 40.20100502512563,
|
| 116 |
-
"2012 Falĺ": 40.30612244897959,
|
| 117 |
-
"2022 Spring": 38.265306122448976,
|
| 118 |
-
"2014 Spring": 37.94871794871795,
|
| 119 |
-
"2022 Fall": 38.775510204081634,
|
| 120 |
-
"2014 Fall": 36.97916666666667,
|
| 121 |
-
"2024 Spring": 42.63959390862944,
|
| 122 |
-
"2015 Spring": 40.4040404040404,
|
| 123 |
-
"2023 Spring": 37.628865979381445,
|
| 124 |
-
"2021 Fall": 42.2680412371134,
|
| 125 |
-
"2015 Fall": 34.73684210526316,
|
| 126 |
-
"2023 Fall": 42.78350515463917,
|
| 127 |
-
"2021 Spring": 39.0,
|
| 128 |
-
"2013 Spring": 34.375,
|
| 129 |
-
"2013 Fall": 43.97905759162304,
|
| 130 |
-
"overall_accuracy": 39.308905380333954
|
| 131 |
-
},
|
| 132 |
{
|
| 133 |
"model_name": "model-gpt-4o-mini-2024-07-18",
|
| 134 |
"2011 Spring": 75.75757575757575,
|
| 135 |
"2010 Spring": 74.5,
|
| 136 |
-
"2008 Fall
|
| 137 |
-
"2011 Fall
|
| 138 |
-
"2009 Fall
|
| 139 |
-
"2010 Fall
|
| 140 |
"2012 Spring": 75.0,
|
| 141 |
"2009 Spring": 72.8643216080402,
|
| 142 |
-
"2012 Fall
|
| 143 |
"2022 Spring": 70.40816326530613,
|
| 144 |
"2014 Spring": 72.82051282051282,
|
| 145 |
"2022 Fall": 76.53061224489795,
|
|
@@ -159,13 +211,13 @@
|
|
| 159 |
"model_name": "model-meta-llama-Llama-3.2-1B-Instruct",
|
| 160 |
"2011 Spring": 18.181818181818183,
|
| 161 |
"2010 Spring": 25.5,
|
| 162 |
-
"2008 Fall
|
| 163 |
-
"2011 Fall
|
| 164 |
-
"2009 Fall
|
| 165 |
-
"2010 Fall
|
| 166 |
"2012 Spring": 29.5,
|
| 167 |
"2009 Spring": 29.145728643216078,
|
| 168 |
-
"2012 Fall
|
| 169 |
"2022 Spring": 20.918367346938776,
|
| 170 |
"2014 Spring": 25.64102564102564,
|
| 171 |
"2022 Fall": 23.46938775510204,
|
|
@@ -182,68 +234,42 @@
|
|
| 182 |
"overall_accuracy": 24.81447124304267
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"model_name": "model-
|
| 186 |
-
"2011 Spring":
|
| 187 |
-
"2010 Spring":
|
| 188 |
-
"2008 Fall
|
| 189 |
-
"2011 Fall
|
| 190 |
-
"2009 Fall
|
| 191 |
-
"2010 Fall
|
| 192 |
-
"2012 Spring":
|
| 193 |
-
"2009 Spring":
|
| 194 |
-
"2012 Fall
|
| 195 |
-
"2022 Spring":
|
| 196 |
-
"2014 Spring":
|
| 197 |
-
"2022 Fall":
|
| 198 |
-
"2014 Fall":
|
| 199 |
-
"2024 Spring":
|
| 200 |
-
"2015 Spring":
|
| 201 |
-
"2023 Spring":
|
| 202 |
-
"2021 Fall":
|
| 203 |
-
"2015 Fall":
|
| 204 |
-
"2023 Fall":
|
| 205 |
-
"2021 Spring":
|
| 206 |
-
"2013 Spring":
|
| 207 |
-
"2013 Fall":
|
| 208 |
-
"overall_accuracy":
|
| 209 |
-
},
|
| 210 |
-
{
|
| 211 |
-
"model_name": "model-meta-llama-Meta-Llama-3.1-8B-Instruct",
|
| 212 |
-
"2011 Spring": 53.03030303030303,
|
| 213 |
-
"2010 Spring": 54.0,
|
| 214 |
-
"2008 Falĺ": 51.26903553299492,
|
| 215 |
-
"2011 Falĺ": 56.56565656565656,
|
| 216 |
-
"2009 Falĺ": 47.20812182741117,
|
| 217 |
-
"2010 Falĺ": 43.43434343434344,
|
| 218 |
-
"2012 Spring": 53.0,
|
| 219 |
-
"2009 Spring": 45.22613065326633,
|
| 220 |
-
"2012 Falĺ": 52.55102040816326,
|
| 221 |
-
"2022 Spring": 45.91836734693878,
|
| 222 |
-
"2014 Spring": 52.307692307692314,
|
| 223 |
-
"2022 Fall": 53.06122448979592,
|
| 224 |
-
"2014 Fall": 53.125,
|
| 225 |
-
"2024 Spring": 57.868020304568525,
|
| 226 |
-
"2015 Spring": 54.54545454545454,
|
| 227 |
-
"2023 Spring": 51.03092783505154,
|
| 228 |
-
"2021 Fall": 52.0618556701031,
|
| 229 |
-
"2015 Fall": 44.73684210526316,
|
| 230 |
-
"2023 Fall": 48.45360824742268,
|
| 231 |
-
"2021 Spring": 47.0,
|
| 232 |
-
"2013 Spring": 54.166666666666664,
|
| 233 |
-
"2013 Fall": 51.832460732984295,
|
| 234 |
-
"overall_accuracy": 51.02040816326531
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"model_name": "model-aaditya-Llama3-OpenBioLLM-70B",
|
| 238 |
"2011 Spring": 23.232323232323232,
|
| 239 |
"2010 Spring": 18.0,
|
| 240 |
-
"2008 Fall
|
| 241 |
-
"2011 Fall
|
| 242 |
-
"2009 Fall
|
| 243 |
-
"2010 Fall
|
| 244 |
"2012 Spring": 61.0,
|
| 245 |
"2009 Spring": 54.2713567839196,
|
| 246 |
-
"2012 Fall
|
| 247 |
"2022 Spring": 60.204081632653065,
|
| 248 |
"2014 Spring": 57.43589743589743,
|
| 249 |
"2022 Fall": 57.6530612244898,
|
|
@@ -260,42 +286,68 @@
|
|
| 260 |
"overall_accuracy": 55.14842300556586
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"model_name": "model-
|
| 264 |
-
"2011 Spring":
|
| 265 |
-
"2010 Spring":
|
| 266 |
-
"2008 Fall
|
| 267 |
-
"2011 Fall
|
| 268 |
-
"2009 Fall
|
| 269 |
-
"2010 Fall
|
| 270 |
-
"2012 Spring":
|
| 271 |
-
"2009 Spring":
|
| 272 |
-
"2012 Fall
|
| 273 |
-
"2022 Spring":
|
| 274 |
-
"2014 Spring":
|
| 275 |
-
"2022 Fall":
|
| 276 |
-
"2014 Fall":
|
| 277 |
-
"2024 Spring":
|
| 278 |
-
"2015 Spring":
|
| 279 |
-
"2023 Spring":
|
| 280 |
-
"2021 Fall":
|
| 281 |
-
"2015 Fall":
|
| 282 |
-
"2023 Fall":
|
| 283 |
-
"2021 Spring":
|
| 284 |
-
"2013 Spring":
|
| 285 |
-
"2013 Fall":
|
| 286 |
-
"overall_accuracy":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"model_name": "model-meta-llama-Meta-Llama-3.1-70B-Instruct",
|
| 290 |
"2011 Spring": 77.27272727272727,
|
| 291 |
"2010 Spring": 82.0,
|
| 292 |
-
"2008 Fall
|
| 293 |
-
"2011 Fall
|
| 294 |
-
"2009 Fall
|
| 295 |
-
"2010 Fall
|
| 296 |
"2012 Spring": 80.0,
|
| 297 |
"2009 Spring": 72.8643216080402,
|
| 298 |
-
"2012 Fall
|
| 299 |
"2022 Spring": 79.59183673469387,
|
| 300 |
"2014 Spring": 76.41025641025641,
|
| 301 |
"2022 Fall": 82.14285714285714,
|
|
@@ -311,69 +363,17 @@
|
|
| 311 |
"2013 Fall": 78.01047120418848,
|
| 312 |
"overall_accuracy": 80.47309833024119
|
| 313 |
},
|
| 314 |
-
{
|
| 315 |
-
"model_name": "model-johnsnowlabs-JSL-MedLlama-3-8B-v2.0",
|
| 316 |
-
"2011 Spring": 37.37373737373738,
|
| 317 |
-
"2010 Spring": 38.5,
|
| 318 |
-
"2008 Falĺ": 38.07106598984771,
|
| 319 |
-
"2011 Falĺ": 42.92929292929293,
|
| 320 |
-
"2009 Falĺ": 31.979695431472084,
|
| 321 |
-
"2010 Falĺ": 34.84848484848485,
|
| 322 |
-
"2012 Spring": 37.0,
|
| 323 |
-
"2009 Spring": 34.17085427135678,
|
| 324 |
-
"2012 Falĺ": 39.285714285714285,
|
| 325 |
-
"2022 Spring": 34.183673469387756,
|
| 326 |
-
"2014 Spring": 36.92307692307693,
|
| 327 |
-
"2022 Fall": 41.83673469387755,
|
| 328 |
-
"2014 Fall": 35.9375,
|
| 329 |
-
"2024 Spring": 37.055837563451774,
|
| 330 |
-
"2015 Spring": 33.83838383838384,
|
| 331 |
-
"2023 Spring": 32.98969072164948,
|
| 332 |
-
"2021 Fall": 36.597938144329895,
|
| 333 |
-
"2015 Fall": 33.1578947368421,
|
| 334 |
-
"2023 Fall": 38.659793814432994,
|
| 335 |
-
"2021 Spring": 33.5,
|
| 336 |
-
"2013 Spring": 32.8125,
|
| 337 |
-
"2013 Fall": 40.31413612565445,
|
| 338 |
-
"overall_accuracy": 36.45640074211503
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"model_name": "model-BioMistral-BioMistral-7B",
|
| 342 |
-
"2011 Spring": 22.727272727272727,
|
| 343 |
-
"2010 Spring": 25.5,
|
| 344 |
-
"2008 Falĺ": 20.812182741116754,
|
| 345 |
-
"2011 Falĺ": 27.77777777777778,
|
| 346 |
-
"2009 Falĺ": 24.36548223350254,
|
| 347 |
-
"2010 Falĺ": 27.27272727272727,
|
| 348 |
-
"2012 Spring": 27.500000000000004,
|
| 349 |
-
"2009 Spring": 28.643216080402013,
|
| 350 |
-
"2012 Falĺ": 22.95918367346939,
|
| 351 |
-
"2022 Spring": 22.95918367346939,
|
| 352 |
-
"2014 Spring": 26.666666666666668,
|
| 353 |
-
"2022 Fall": 24.489795918367346,
|
| 354 |
-
"2014 Fall": 25.520833333333332,
|
| 355 |
-
"2024 Spring": 28.426395939086298,
|
| 356 |
-
"2015 Spring": 27.77777777777778,
|
| 357 |
-
"2023 Spring": 26.288659793814436,
|
| 358 |
-
"2021 Fall": 26.288659793814436,
|
| 359 |
-
"2015 Fall": 30.0,
|
| 360 |
-
"2023 Fall": 24.742268041237114,
|
| 361 |
-
"2021 Spring": 28.000000000000004,
|
| 362 |
-
"2013 Spring": 27.604166666666668,
|
| 363 |
-
"2013 Fall": 22.5130890052356,
|
| 364 |
-
"overall_accuracy": 25.858070500927642
|
| 365 |
-
},
|
| 366 |
{
|
| 367 |
"model_name": "model-ProbeMedicalYonseiMAILab-medllama3-v20",
|
| 368 |
"2011 Spring": 39.8989898989899,
|
| 369 |
"2010 Spring": 46.0,
|
| 370 |
-
"2008 Fall
|
| 371 |
-
"2011 Fall
|
| 372 |
-
"2009 Fall
|
| 373 |
-
"2010 Fall
|
| 374 |
"2012 Spring": 40.5,
|
| 375 |
"2009 Spring": 35.678391959798994,
|
| 376 |
-
"2012 Fall
|
| 377 |
"2022 Spring": 39.285714285714285,
|
| 378 |
"2014 Spring": 37.94871794871795,
|
| 379 |
"2022 Fall": 41.83673469387755,
|
|
@@ -393,13 +393,13 @@
|
|
| 393 |
"model_name": "model-mistralai-Mistral-Small-Instruct-2409",
|
| 394 |
"2011 Spring": 46.464646464646464,
|
| 395 |
"2010 Spring": 54.0,
|
| 396 |
-
"2008 Fall
|
| 397 |
-
"2011 Fall
|
| 398 |
-
"2009 Fall
|
| 399 |
-
"2010 Fall
|
| 400 |
"2012 Spring": 56.49999999999999,
|
| 401 |
"2009 Spring": 52.26130653266332,
|
| 402 |
-
"2012 Fall
|
| 403 |
"2022 Spring": 48.97959183673469,
|
| 404 |
"2014 Spring": 48.205128205128204,
|
| 405 |
"2022 Fall": 52.04081632653062,
|
|
@@ -416,29 +416,29 @@
|
|
| 416 |
"overall_accuracy": 51.36827458256029
|
| 417 |
},
|
| 418 |
{
|
| 419 |
-
"model_name": "model-
|
| 420 |
-
"2011 Spring":
|
| 421 |
-
"2010 Spring":
|
| 422 |
-
"2008 Fall
|
| 423 |
-
"2011 Fall
|
| 424 |
-
"2009 Fall
|
| 425 |
-
"2010 Fall
|
| 426 |
-
"2012 Spring":
|
| 427 |
-
"2009 Spring":
|
| 428 |
-
"2012 Fall
|
| 429 |
-
"2022 Spring":
|
| 430 |
-
"2014 Spring":
|
| 431 |
-
"2022 Fall":
|
| 432 |
-
"2014 Fall":
|
| 433 |
-
"2024 Spring":
|
| 434 |
-
"2015 Spring":
|
| 435 |
-
"2023 Spring":
|
| 436 |
-
"2021 Fall":
|
| 437 |
-
"2015 Fall":
|
| 438 |
-
"2023 Fall":
|
| 439 |
-
"2021 Spring":
|
| 440 |
-
"2013 Spring":
|
| 441 |
-
"2013 Fall":
|
| 442 |
-
"overall_accuracy":
|
| 443 |
}
|
| 444 |
]
|
|
|
|
| 1 |
[
|
| 2 |
{
|
| 3 |
+
"model_name": "model-BioMistral-BioMistral-7B",
|
| 4 |
+
"2011 Spring": 22.727272727272727,
|
| 5 |
+
"2010 Spring": 25.5,
|
| 6 |
+
"2008 Fall": 20.812182741116754,
|
| 7 |
+
"2011 Fall": 27.77777777777778,
|
| 8 |
+
"2009 Fall": 24.36548223350254,
|
| 9 |
+
"2010 Fall": 27.27272727272727,
|
| 10 |
+
"2012 Spring": 27.500000000000004,
|
| 11 |
+
"2009 Spring": 28.643216080402013,
|
| 12 |
+
"2012 Fall": 22.95918367346939,
|
| 13 |
+
"2022 Spring": 22.95918367346939,
|
| 14 |
+
"2014 Spring": 26.666666666666668,
|
| 15 |
+
"2022 Fall": 24.489795918367346,
|
| 16 |
+
"2014 Fall": 25.520833333333332,
|
| 17 |
+
"2024 Spring": 28.426395939086298,
|
| 18 |
+
"2015 Spring": 27.77777777777778,
|
| 19 |
+
"2023 Spring": 26.288659793814436,
|
| 20 |
+
"2021 Fall": 26.288659793814436,
|
| 21 |
+
"2015 Fall": 30.0,
|
| 22 |
+
"2023 Fall": 24.742268041237114,
|
| 23 |
+
"2021 Spring": 28.000000000000004,
|
| 24 |
+
"2013 Spring": 27.604166666666668,
|
| 25 |
+
"2013 Fall": 22.5130890052356,
|
| 26 |
+
"overall_accuracy": 25.858070500927642
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"model_name": "model-johnsnowlabs-JSL-MedLlama-3-8B-v2.0",
|
| 30 |
+
"2011 Spring": 37.37373737373738,
|
| 31 |
+
"2010 Spring": 38.5,
|
| 32 |
+
"2008 Fall": 38.07106598984771,
|
| 33 |
+
"2011 Fall": 42.92929292929293,
|
| 34 |
+
"2009 Fall": 31.979695431472084,
|
| 35 |
+
"2010 Fall": 34.84848484848485,
|
| 36 |
+
"2012 Spring": 37.0,
|
| 37 |
+
"2009 Spring": 34.17085427135678,
|
| 38 |
+
"2012 Fall": 39.285714285714285,
|
| 39 |
+
"2022 Spring": 34.183673469387756,
|
| 40 |
+
"2014 Spring": 36.92307692307693,
|
| 41 |
+
"2022 Fall": 41.83673469387755,
|
| 42 |
+
"2014 Fall": 35.9375,
|
| 43 |
+
"2024 Spring": 37.055837563451774,
|
| 44 |
+
"2015 Spring": 33.83838383838384,
|
| 45 |
+
"2023 Spring": 32.98969072164948,
|
| 46 |
+
"2021 Fall": 36.597938144329895,
|
| 47 |
+
"2015 Fall": 33.1578947368421,
|
| 48 |
+
"2023 Fall": 38.659793814432994,
|
| 49 |
+
"2021 Spring": 33.5,
|
| 50 |
+
"2013 Spring": 32.8125,
|
| 51 |
+
"2013 Fall": 40.31413612565445,
|
| 52 |
+
"overall_accuracy": 36.45640074211503
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"model_name": "model-meta-llama-Meta-Llama-3.1-8B-Instruct",
|
| 56 |
+
"2011 Spring": 53.03030303030303,
|
| 57 |
+
"2010 Spring": 54.0,
|
| 58 |
+
"2008 Fall": 51.26903553299492,
|
| 59 |
+
"2011 Fall": 56.56565656565656,
|
| 60 |
+
"2009 Fall": 47.20812182741117,
|
| 61 |
+
"2010 Fall": 43.43434343434344,
|
| 62 |
+
"2012 Spring": 53.0,
|
| 63 |
+
"2009 Spring": 45.22613065326633,
|
| 64 |
+
"2012 Fall": 52.55102040816326,
|
| 65 |
+
"2022 Spring": 45.91836734693878,
|
| 66 |
+
"2014 Spring": 52.307692307692314,
|
| 67 |
+
"2022 Fall": 53.06122448979592,
|
| 68 |
+
"2014 Fall": 53.125,
|
| 69 |
+
"2024 Spring": 57.868020304568525,
|
| 70 |
+
"2015 Spring": 54.54545454545454,
|
| 71 |
+
"2023 Spring": 51.03092783505154,
|
| 72 |
+
"2021 Fall": 52.0618556701031,
|
| 73 |
+
"2015 Fall": 44.73684210526316,
|
| 74 |
+
"2023 Fall": 48.45360824742268,
|
| 75 |
+
"2021 Spring": 47.0,
|
| 76 |
+
"2013 Spring": 54.166666666666664,
|
| 77 |
+
"2013 Fall": 51.832460732984295,
|
| 78 |
+
"overall_accuracy": 51.02040816326531
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"model_name": "model-Qwen-Qwen2.5-7B-Instruct",
|
| 82 |
+
"2011 Spring": 50.0,
|
| 83 |
+
"2010 Spring": 52.5,
|
| 84 |
+
"2008 Fall": 54.314720812182735,
|
| 85 |
+
"2011 Fall": 59.59595959595959,
|
| 86 |
+
"2009 Fall": 45.68527918781726,
|
| 87 |
+
"2010 Fall": 48.484848484848484,
|
| 88 |
+
"2012 Spring": 45.0,
|
| 89 |
+
"2009 Spring": 51.75879396984925,
|
| 90 |
+
"2012 Fall": 48.97959183673469,
|
| 91 |
+
"2022 Spring": 50.0,
|
| 92 |
+
"2014 Spring": 48.717948717948715,
|
| 93 |
+
"2022 Fall": 52.55102040816326,
|
| 94 |
+
"2014 Fall": 53.645833333333336,
|
| 95 |
+
"2024 Spring": 55.32994923857868,
|
| 96 |
+
"2015 Spring": 47.474747474747474,
|
| 97 |
+
"2023 Spring": 51.546391752577314,
|
| 98 |
+
"2021 Fall": 58.24742268041238,
|
| 99 |
+
"2015 Fall": 50.0,
|
| 100 |
+
"2023 Fall": 50.0,
|
| 101 |
+
"2021 Spring": 50.5,
|
| 102 |
+
"2013 Spring": 56.770833333333336,
|
| 103 |
+
"2013 Fall": 50.26178010471204,
|
| 104 |
+
"overall_accuracy": 51.41465677179963
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"model_name": "model-gpt-4o-2024-08-06",
|
| 108 |
"2011 Spring": 87.37373737373737,
|
| 109 |
"2010 Spring": 88.5,
|
| 110 |
+
"2008 Fall": 88.3248730964467,
|
| 111 |
+
"2011 Fall": 90.40404040404042,
|
| 112 |
+
"2009 Fall": 87.81725888324873,
|
| 113 |
+
"2010 Fall": 89.39393939393939,
|
| 114 |
"2012 Spring": 90.0,
|
| 115 |
"2009 Spring": 86.93467336683418,
|
| 116 |
+
"2012 Fall": 88.77551020408163,
|
| 117 |
"2022 Spring": 89.28571428571429,
|
| 118 |
"2014 Spring": 88.71794871794872,
|
| 119 |
"2022 Fall": 91.3265306122449,
|
|
|
|
| 130 |
"overall_accuracy": 89.40166975881262
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"model_name": "model-speakleash-Bielik-11B-v2.2-Instruct",
|
| 134 |
+
"2011 Spring": 59.59595959595959,
|
| 135 |
+
"2010 Spring": 62.0,
|
| 136 |
+
"2008 Fall": 59.89847715736041,
|
| 137 |
+
"2011 Fall": 60.1010101010101,
|
| 138 |
+
"2009 Fall": 58.37563451776649,
|
| 139 |
+
"2010 Fall": 63.13131313131313,
|
| 140 |
+
"2012 Spring": 61.0,
|
| 141 |
+
"2009 Spring": 63.31658291457286,
|
| 142 |
+
"2012 Fall": 63.26530612244898,
|
| 143 |
+
"2022 Spring": 58.16326530612245,
|
| 144 |
+
"2014 Spring": 57.948717948717956,
|
| 145 |
+
"2022 Fall": 67.85714285714286,
|
| 146 |
+
"2014 Fall": 63.541666666666664,
|
| 147 |
+
"2024 Spring": 65.48223350253807,
|
| 148 |
+
"2015 Spring": 59.59595959595959,
|
| 149 |
+
"2023 Spring": 63.4020618556701,
|
| 150 |
+
"2021 Fall": 62.371134020618555,
|
| 151 |
+
"2015 Fall": 61.578947368421055,
|
| 152 |
+
"2023 Fall": 62.88659793814433,
|
| 153 |
+
"2021 Spring": 64.5,
|
| 154 |
+
"2013 Spring": 61.458333333333336,
|
| 155 |
+
"2013 Fall": 61.78010471204188,
|
| 156 |
+
"overall_accuracy": 61.87384044526901
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"model_name": "model-OpenMeditron-Meditron3-8B",
|
| 160 |
"2011 Spring": 43.93939393939394,
|
| 161 |
"2010 Spring": 48.0,
|
| 162 |
+
"2008 Fall": 46.192893401015226,
|
| 163 |
+
"2011 Fall": 47.474747474747474,
|
| 164 |
+
"2009 Fall": 46.7005076142132,
|
| 165 |
+
"2010 Fall": 40.4040404040404,
|
| 166 |
"2012 Spring": 43.5,
|
| 167 |
"2009 Spring": 43.21608040201005,
|
| 168 |
+
"2012 Fall": 45.40816326530612,
|
| 169 |
"2022 Spring": 41.83673469387755,
|
| 170 |
"2014 Spring": 42.05128205128205,
|
| 171 |
"2022 Fall": 43.36734693877551,
|
|
|
|
| 181 |
"2013 Fall": 51.832460732984295,
|
| 182 |
"overall_accuracy": 45.570500927643785
|
| 183 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 184 |
{
|
| 185 |
"model_name": "model-gpt-4o-mini-2024-07-18",
|
| 186 |
"2011 Spring": 75.75757575757575,
|
| 187 |
"2010 Spring": 74.5,
|
| 188 |
+
"2008 Fall": 77.15736040609137,
|
| 189 |
+
"2011 Fall": 72.72727272727273,
|
| 190 |
+
"2009 Fall": 71.06598984771574,
|
| 191 |
+
"2010 Fall": 75.75757575757575,
|
| 192 |
"2012 Spring": 75.0,
|
| 193 |
"2009 Spring": 72.8643216080402,
|
| 194 |
+
"2012 Fall": 78.57142857142857,
|
| 195 |
"2022 Spring": 70.40816326530613,
|
| 196 |
"2014 Spring": 72.82051282051282,
|
| 197 |
"2022 Fall": 76.53061224489795,
|
|
|
|
| 211 |
"model_name": "model-meta-llama-Llama-3.2-1B-Instruct",
|
| 212 |
"2011 Spring": 18.181818181818183,
|
| 213 |
"2010 Spring": 25.5,
|
| 214 |
+
"2008 Fall": 20.304568527918782,
|
| 215 |
+
"2011 Fall": 30.303030303030305,
|
| 216 |
+
"2009 Fall": 25.380710659898476,
|
| 217 |
+
"2010 Fall": 23.737373737373737,
|
| 218 |
"2012 Spring": 29.5,
|
| 219 |
"2009 Spring": 29.145728643216078,
|
| 220 |
+
"2012 Fall": 26.53061224489796,
|
| 221 |
"2022 Spring": 20.918367346938776,
|
| 222 |
"2014 Spring": 25.64102564102564,
|
| 223 |
"2022 Fall": 23.46938775510204,
|
|
|
|
| 234 |
"overall_accuracy": 24.81447124304267
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"model_name": "model-OpenMeditron-Meditron3-70B",
|
| 238 |
+
"2011 Spring": 64.14141414141415,
|
| 239 |
+
"2010 Spring": 73.5,
|
| 240 |
+
"2008 Fall": 62.43654822335025,
|
| 241 |
+
"2011 Fall": 69.1919191919192,
|
| 242 |
+
"2009 Fall": 58.88324873096447,
|
| 243 |
+
"2010 Fall": 61.111111111111114,
|
| 244 |
+
"2012 Spring": 68.5,
|
| 245 |
+
"2009 Spring": 59.2964824120603,
|
| 246 |
+
"2012 Fall": 66.83673469387756,
|
| 247 |
+
"2022 Spring": 70.91836734693877,
|
| 248 |
+
"2014 Spring": 70.25641025641025,
|
| 249 |
+
"2022 Fall": 63.775510204081634,
|
| 250 |
+
"2014 Fall": 69.27083333333334,
|
| 251 |
+
"2024 Spring": 77.66497461928934,
|
| 252 |
+
"2015 Spring": 67.67676767676768,
|
| 253 |
+
"2023 Spring": 67.0103092783505,
|
| 254 |
+
"2021 Fall": 64.43298969072166,
|
| 255 |
+
"2015 Fall": 66.3157894736842,
|
| 256 |
+
"2023 Fall": 68.55670103092784,
|
| 257 |
+
"2021 Spring": 70.5,
|
| 258 |
+
"2013 Spring": 65.625,
|
| 259 |
+
"2013 Fall": 66.49214659685863,
|
| 260 |
+
"overall_accuracy": 66.92949907235621
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"model_name": "model-aaditya-Llama3-OpenBioLLM-70B",
|
| 264 |
"2011 Spring": 23.232323232323232,
|
| 265 |
"2010 Spring": 18.0,
|
| 266 |
+
"2008 Fall": 36.04060913705584,
|
| 267 |
+
"2011 Fall": 58.58585858585859,
|
| 268 |
+
"2009 Fall": 54.314720812182735,
|
| 269 |
+
"2010 Fall": 54.04040404040404,
|
| 270 |
"2012 Spring": 61.0,
|
| 271 |
"2009 Spring": 54.2713567839196,
|
| 272 |
+
"2012 Fall": 58.16326530612245,
|
| 273 |
"2022 Spring": 60.204081632653065,
|
| 274 |
"2014 Spring": 57.43589743589743,
|
| 275 |
"2022 Fall": 57.6530612244898,
|
|
|
|
| 286 |
"overall_accuracy": 55.14842300556586
|
| 287 |
},
|
| 288 |
{
|
| 289 |
+
"model_name": "model-meta-llama-Llama-3.2-3B-Instruct",
|
| 290 |
+
"2011 Spring": 36.868686868686865,
|
| 291 |
+
"2010 Spring": 38.0,
|
| 292 |
+
"2008 Fall": 38.578680203045685,
|
| 293 |
+
"2011 Fall": 47.97979797979798,
|
| 294 |
+
"2009 Fall": 38.578680203045685,
|
| 295 |
+
"2010 Fall": 38.38383838383838,
|
| 296 |
+
"2012 Spring": 36.0,
|
| 297 |
+
"2009 Spring": 40.20100502512563,
|
| 298 |
+
"2012 Fall": 40.30612244897959,
|
| 299 |
+
"2022 Spring": 38.265306122448976,
|
| 300 |
+
"2014 Spring": 37.94871794871795,
|
| 301 |
+
"2022 Fall": 38.775510204081634,
|
| 302 |
+
"2014 Fall": 36.97916666666667,
|
| 303 |
+
"2024 Spring": 42.63959390862944,
|
| 304 |
+
"2015 Spring": 40.4040404040404,
|
| 305 |
+
"2023 Spring": 37.628865979381445,
|
| 306 |
+
"2021 Fall": 42.2680412371134,
|
| 307 |
+
"2015 Fall": 34.73684210526316,
|
| 308 |
+
"2023 Fall": 42.78350515463917,
|
| 309 |
+
"2021 Spring": 39.0,
|
| 310 |
+
"2013 Spring": 34.375,
|
| 311 |
+
"2013 Fall": 43.97905759162304,
|
| 312 |
+
"overall_accuracy": 39.308905380333954
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"model_name": "model-mistralai-Mistral-Large-Instruct-2407",
|
| 316 |
+
"2011 Spring": 76.26262626262627,
|
| 317 |
+
"2010 Spring": 76.5,
|
| 318 |
+
"2008 Fall": 76.6497461928934,
|
| 319 |
+
"2011 Fall": 79.29292929292929,
|
| 320 |
+
"2009 Fall": 71.57360406091371,
|
| 321 |
+
"2010 Fall": 74.24242424242425,
|
| 322 |
+
"2012 Spring": 77.5,
|
| 323 |
+
"2009 Spring": 72.8643216080402,
|
| 324 |
+
"2012 Fall": 76.53061224489795,
|
| 325 |
+
"2022 Spring": 72.95918367346938,
|
| 326 |
+
"2014 Spring": 80.0,
|
| 327 |
+
"2022 Fall": 75.0,
|
| 328 |
+
"2014 Fall": 76.5625,
|
| 329 |
+
"2024 Spring": 86.80203045685279,
|
| 330 |
+
"2015 Spring": 75.25252525252525,
|
| 331 |
+
"2023 Spring": 79.38144329896907,
|
| 332 |
+
"2021 Fall": 76.28865979381443,
|
| 333 |
+
"2015 Fall": 71.05263157894737,
|
| 334 |
+
"2023 Fall": 76.80412371134021,
|
| 335 |
+
"2021 Spring": 79.5,
|
| 336 |
+
"2013 Spring": 71.875,
|
| 337 |
+
"2013 Fall": 75.91623036649214,
|
| 338 |
+
"overall_accuracy": 76.32189239332097
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"model_name": "model-meta-llama-Meta-Llama-3.1-70B-Instruct",
|
| 342 |
"2011 Spring": 77.27272727272727,
|
| 343 |
"2010 Spring": 82.0,
|
| 344 |
+
"2008 Fall": 79.69543147208121,
|
| 345 |
+
"2011 Fall": 83.33333333333334,
|
| 346 |
+
"2009 Fall": 81.21827411167513,
|
| 347 |
+
"2010 Fall": 80.8080808080808,
|
| 348 |
"2012 Spring": 80.0,
|
| 349 |
"2009 Spring": 72.8643216080402,
|
| 350 |
+
"2012 Fall": 81.12244897959184,
|
| 351 |
"2022 Spring": 79.59183673469387,
|
| 352 |
"2014 Spring": 76.41025641025641,
|
| 353 |
"2022 Fall": 82.14285714285714,
|
|
|
|
| 363 |
"2013 Fall": 78.01047120418848,
|
| 364 |
"overall_accuracy": 80.47309833024119
|
| 365 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 366 |
{
|
| 367 |
"model_name": "model-ProbeMedicalYonseiMAILab-medllama3-v20",
|
| 368 |
"2011 Spring": 39.8989898989899,
|
| 369 |
"2010 Spring": 46.0,
|
| 370 |
+
"2008 Fall": 38.07106598984771,
|
| 371 |
+
"2011 Fall": 40.4040404040404,
|
| 372 |
+
"2009 Fall": 36.04060913705584,
|
| 373 |
+
"2010 Fall": 38.38383838383838,
|
| 374 |
"2012 Spring": 40.5,
|
| 375 |
"2009 Spring": 35.678391959798994,
|
| 376 |
+
"2012 Fall": 46.42857142857143,
|
| 377 |
"2022 Spring": 39.285714285714285,
|
| 378 |
"2014 Spring": 37.94871794871795,
|
| 379 |
"2022 Fall": 41.83673469387755,
|
|
|
|
| 393 |
"model_name": "model-mistralai-Mistral-Small-Instruct-2409",
|
| 394 |
"2011 Spring": 46.464646464646464,
|
| 395 |
"2010 Spring": 54.0,
|
| 396 |
+
"2008 Fall": 51.26903553299492,
|
| 397 |
+
"2011 Fall": 52.02020202020202,
|
| 398 |
+
"2009 Fall": 45.68527918781726,
|
| 399 |
+
"2010 Fall": 50.0,
|
| 400 |
"2012 Spring": 56.49999999999999,
|
| 401 |
"2009 Spring": 52.26130653266332,
|
| 402 |
+
"2012 Fall": 49.48979591836735,
|
| 403 |
"2022 Spring": 48.97959183673469,
|
| 404 |
"2014 Spring": 48.205128205128204,
|
| 405 |
"2022 Fall": 52.04081632653062,
|
|
|
|
| 416 |
"overall_accuracy": 51.36827458256029
|
| 417 |
},
|
| 418 |
{
|
| 419 |
+
"model_name": "model-Qwen-Qwen2.5-72B-Instruct",
|
| 420 |
+
"2011 Spring": 75.25252525252525,
|
| 421 |
+
"2010 Spring": 76.0,
|
| 422 |
+
"2008 Fall": 80.71065989847716,
|
| 423 |
+
"2011 Fall": 73.73737373737373,
|
| 424 |
+
"2009 Fall": 71.06598984771574,
|
| 425 |
+
"2010 Fall": 74.74747474747475,
|
| 426 |
+
"2012 Spring": 79.0,
|
| 427 |
+
"2009 Spring": 74.87437185929649,
|
| 428 |
+
"2012 Fall": 76.0204081632653,
|
| 429 |
+
"2022 Spring": 72.95918367346938,
|
| 430 |
+
"2014 Spring": 77.43589743589745,
|
| 431 |
+
"2022 Fall": 77.04081632653062,
|
| 432 |
+
"2014 Fall": 84.375,
|
| 433 |
+
"2024 Spring": 81.21827411167513,
|
| 434 |
+
"2015 Spring": 75.25252525252525,
|
| 435 |
+
"2023 Spring": 77.83505154639175,
|
| 436 |
+
"2021 Fall": 73.19587628865979,
|
| 437 |
+
"2015 Fall": 73.15789473684211,
|
| 438 |
+
"2023 Fall": 76.28865979381443,
|
| 439 |
+
"2021 Spring": 78.5,
|
| 440 |
+
"2013 Spring": 72.91666666666666,
|
| 441 |
+
"2013 Fall": 79.05759162303664,
|
| 442 |
+
"overall_accuracy": 76.39146567717997
|
| 443 |
}
|
| 444 |
]
|