michal commited on
Commit
bdc3484
·
1 Parent(s): abe54b6
Files changed (2) hide show
  1. leaderboards/ldek_accs.json +404 -404
  2. leaderboards/lek_accs.json +406 -406
leaderboards/ldek_accs.json CHANGED
@@ -1,444 +1,444 @@
1
  [
2
  {
3
- "model_name": "model-meta-llama-Meta-Llama-3.1-8B-Instruct",
4
- "2008_jesień": 40.4040404040404,
5
- "2012_wiosna": 40.72164948453608,
6
- "2010_jesień": 43.71859296482412,
7
- "2009_wiosna": 47.97979797979798,
8
- "2010_wiosna": 46.0,
9
- "2011_wiosna": 33.83838383838384,
10
- "2012_jesień": 50.0,
11
- "2011_jesień": 41.41414141414141,
12
- "2009_jesień": 54.0,
13
- "2022_wiosna": 38.88888888888889,
14
- "2014_wiosna": 33.16326530612245,
15
- "2022_jesien": 40.816326530612244,
16
- "2014_jesien": 42.487046632124354,
17
- "2024_wiosna": 39.59390862944163,
18
- "2015_wiosna": 42.473118279569896,
19
- "2023_wiosna": 44.94949494949495,
20
- "2021_jesien": 40.909090909090914,
21
- "2015_jesien": 41.578947368421055,
22
- "2023_jesien": 42.05128205128205,
23
- "2021_wiosna": 41.3265306122449,
24
- "2013_wiosna": 41.23711340206185,
25
- "2013_jesien": 44.50261780104712,
26
- "overall_accuracy": 42.37642144349037
27
- },
28
- {
29
- "model_name": "model-meta-llama-Meta-Llama-3.1-70B-Instruct",
30
- "2008_jesień": 62.121212121212125,
31
- "2012_wiosna": 61.34020618556701,
32
- "2010_jesień": 62.8140703517588,
33
- "2009_wiosna": 69.1919191919192,
34
- "2010_wiosna": 73.0,
35
- "2011_wiosna": 59.59595959595959,
36
- "2012_jesień": 69.89795918367348,
37
- "2011_jesień": 65.65656565656566,
38
- "2009_jesień": 68.0,
39
- "2022_wiosna": 68.68686868686868,
40
- "2014_wiosna": 54.59183673469388,
41
- "2022_jesien": 62.755102040816325,
42
- "2014_jesien": 60.62176165803109,
43
- "2024_wiosna": 61.42131979695431,
44
- "2015_wiosna": 60.215053763440864,
45
- "2023_wiosna": 62.62626262626263,
46
- "2021_jesien": 64.14141414141415,
47
- "2015_jesien": 58.42105263157895,
48
- "2023_jesien": 61.02564102564103,
49
- "2021_wiosna": 68.36734693877551,
50
- "2013_wiosna": 62.371134020618555,
51
- "2013_jesien": 57.06806282722513,
52
- "overall_accuracy": 63.402181480621955
53
  },
54
  {
55
  "model_name": "model-Qwen-Qwen2.5-72B-Instruct",
56
- "2008_jesień": 58.58585858585859,
57
- "2012_wiosna": 56.70103092783505,
58
- "2010_jesień": 60.80402010050251,
59
- "2009_wiosna": 60.1010101010101,
60
- "2010_wiosna": 63.5,
61
- "2011_wiosna": 58.58585858585859,
62
- "2012_jesień": 66.83673469387756,
63
- "2011_jesień": 54.54545454545454,
64
- "2009_jesień": 70.5,
65
- "2022_wiosna": 59.59595959595959,
66
- "2014_wiosna": 53.57142857142857,
67
- "2022_jesien": 61.73469387755102,
68
- "2014_jesien": 61.6580310880829,
69
- "2024_wiosna": 57.360406091370564,
70
- "2015_wiosna": 58.602150537634415,
71
- "2023_wiosna": 56.56565656565656,
72
- "2021_jesien": 59.59595959595959,
73
- "2015_jesien": 57.36842105263158,
74
- "2023_jesien": 54.871794871794876,
75
- "2021_wiosna": 58.673469387755105,
76
- "2013_wiosna": 61.855670103092784,
77
- "2013_jesien": 57.06806282722513,
78
  "overall_accuracy": 59.503365049895564
79
  },
80
- {
81
- "model_name": "model-gpt-4o-mini-2024-07-18",
82
- "2008_jesień": 59.09090909090909,
83
- "2012_wiosna": 55.670103092783506,
84
- "2010_jesień": 55.27638190954774,
85
- "2009_wiosna": 68.18181818181817,
86
- "2010_wiosna": 62.5,
87
- "2011_wiosna": 50.0,
88
- "2012_jesień": 65.3061224489796,
89
- "2011_jesień": 55.05050505050505,
90
- "2009_jesień": 64.0,
91
- "2022_wiosna": 52.52525252525253,
92
- "2014_wiosna": 46.93877551020408,
93
- "2022_jesien": 54.08163265306123,
94
- "2014_jesien": 57.51295336787565,
95
- "2024_wiosna": 56.34517766497462,
96
- "2015_wiosna": 52.68817204301075,
97
- "2023_wiosna": 53.535353535353536,
98
- "2021_jesien": 58.080808080808076,
99
- "2015_jesien": 57.89473684210527,
100
- "2023_jesien": 58.46153846153847,
101
- "2021_wiosna": 59.693877551020414,
102
- "2013_wiosna": 55.154639175257735,
103
- "2013_jesien": 51.30890052356021,
104
- "overall_accuracy": 56.811325133441635
105
- },
106
- {
107
- "model_name": "model-aaditya-Llama3-OpenBioLLM-70B",
108
- "2008_jesień": 19.19191919191919,
109
- "2012_wiosna": 19.072164948453608,
110
- "2010_jesień": 35.175879396984925,
111
- "2009_wiosna": 50.0,
112
- "2010_wiosna": 43.0,
113
- "2011_wiosna": 38.88888888888889,
114
- "2012_jesień": 43.36734693877551,
115
- "2011_jesień": 35.35353535353536,
116
- "2009_jesień": 48.0,
117
- "2022_wiosna": 45.95959595959596,
118
- "2014_wiosna": 39.285714285714285,
119
- "2022_jesien": 43.36734693877551,
120
- "2014_jesien": 39.37823834196891,
121
- "2024_wiosna": 44.16243654822335,
122
- "2015_wiosna": 41.39784946236559,
123
- "2023_wiosna": 42.92929292929293,
124
- "2021_jesien": 42.92929292929293,
125
- "2015_jesien": 38.421052631578945,
126
- "2023_jesien": 38.97435897435898,
127
- "2021_wiosna": 41.83673469387755,
128
- "2013_wiosna": 41.23711340206185,
129
- "2013_jesien": 42.93193717277487,
130
- "overall_accuracy": 39.777210489672775
131
- },
132
- {
133
- "model_name": "model-mistralai-Mistral-Large-Instruct-2407",
134
- "2008_jesień": 61.61616161616161,
135
- "2012_wiosna": 54.123711340206185,
136
- "2010_jesień": 62.311557788944725,
137
- "2009_wiosna": 67.67676767676768,
138
- "2010_wiosna": 69.5,
139
- "2011_wiosna": 56.56565656565656,
140
- "2012_jesień": 66.3265306122449,
141
- "2011_jesień": 58.080808080808076,
142
- "2009_jesień": 63.0,
143
- "2022_wiosna": 54.54545454545454,
144
- "2014_wiosna": 54.08163265306123,
145
- "2022_jesien": 56.63265306122449,
146
- "2014_jesien": 56.476683937823836,
147
- "2024_wiosna": 55.83756345177665,
148
- "2015_wiosna": 58.602150537634415,
149
- "2023_wiosna": 57.57575757575758,
150
- "2021_jesien": 56.060606060606055,
151
- "2015_jesien": 60.0,
152
- "2023_jesien": 48.205128205128204,
153
- "2021_wiosna": 57.14285714285714,
154
- "2013_wiosna": 61.34020618556701,
155
- "2013_jesien": 55.497382198952884,
156
- "overall_accuracy": 58.71431886748666
157
- },
158
  {
159
  "model_name": "model-OpenMeditron-Meditron3-8B",
160
- "2008_jesień": 38.88888888888889,
161
- "2012_wiosna": 39.69072164948454,
162
- "2010_jesień": 36.18090452261307,
163
- "2009_wiosna": 41.41414141414141,
164
- "2010_wiosna": 43.0,
165
- "2011_wiosna": 32.82828282828283,
166
- "2012_jesień": 42.3469387755102,
167
- "2011_jesień": 33.33333333333333,
168
- "2009_jesień": 41.5,
169
- "2022_wiosna": 34.34343434343434,
170
- "2014_wiosna": 30.102040816326532,
171
- "2022_jesien": 36.734693877551024,
172
- "2014_jesien": 39.89637305699482,
173
- "2024_wiosna": 38.07106598984771,
174
- "2015_wiosna": 36.55913978494624,
175
- "2023_wiosna": 38.38383838383838,
176
- "2021_jesien": 41.41414141414141,
177
- "2015_jesien": 39.473684210526315,
178
- "2023_jesien": 34.35897435897436,
179
- "2021_wiosna": 40.816326530612244,
180
- "2013_wiosna": 42.78350515463917,
181
- "2013_jesien": 40.83769633507853,
182
  "overall_accuracy": 38.31515432815038
183
  },
184
  {
185
- "model_name": "model-meta-llama-Llama-3.2-1B-Instruct",
186
- "2008_jesień": 24.242424242424242,
187
- "2012_wiosna": 20.618556701030926,
188
- "2010_jesień": 23.618090452261306,
189
- "2009_wiosna": 24.242424242424242,
190
- "2010_wiosna": 23.0,
191
- "2011_wiosna": 24.747474747474747,
192
- "2012_jesień": 28.57142857142857,
193
- "2011_jesień": 21.71717171717172,
194
- "2009_jesień": 25.5,
195
- "2022_wiosna": 21.21212121212121,
196
- "2014_wiosna": 22.448979591836736,
197
- "2022_jesien": 29.591836734693878,
198
- "2014_jesien": 23.316062176165804,
199
- "2024_wiosna": 33.50253807106599,
200
- "2015_wiosna": 23.655913978494624,
201
- "2023_wiosna": 28.28282828282828,
202
- "2021_jesien": 27.27272727272727,
203
- "2015_jesien": 24.736842105263158,
204
- "2023_jesien": 27.692307692307693,
205
- "2021_wiosna": 22.448979591836736,
206
- "2013_wiosna": 23.711340206185564,
207
- "2013_jesien": 27.748691099476442,
208
- "overall_accuracy": 25.08702715247157
209
- },
210
- {
211
- "model_name": "model-OpenMeditron-Meditron3-70B",
212
- "2008_jesień": 45.95959595959596,
213
- "2012_wiosna": 43.29896907216495,
214
- "2010_jesień": 46.733668341708544,
215
- "2009_wiosna": 51.010101010101,
216
- "2010_wiosna": 49.0,
217
- "2011_wiosna": 42.42424242424242,
218
- "2012_jesień": 47.44897959183674,
219
- "2011_jesień": 46.96969696969697,
220
- "2009_jesień": 49.0,
221
- "2022_wiosna": 45.95959595959596,
222
- "2014_wiosna": 41.83673469387755,
223
- "2022_jesien": 48.46938775510204,
224
- "2014_jesien": 47.15025906735752,
225
- "2024_wiosna": 52.28426395939086,
226
- "2015_wiosna": 50.53763440860215,
227
- "2023_wiosna": 47.474747474747474,
228
- "2021_jesien": 48.98989898989899,
229
- "2015_jesien": 51.05263157894737,
230
- "2023_jesien": 42.56410256410256,
231
- "2021_wiosna": 45.40816326530612,
232
- "2013_wiosna": 49.48453608247423,
233
- "2013_jesien": 45.54973821989529,
234
- "overall_accuracy": 47.203527500580186
235
  },
236
  {
237
- "model_name": "model-ProbeMedicalYonseiMAILab-medllama3-v20",
238
- "2008_jesień": 30.303030303030305,
239
- "2012_wiosna": 31.958762886597935,
240
- "2010_jesień": 30.15075376884422,
241
- "2009_wiosna": 37.37373737373738,
242
- "2010_wiosna": 31.5,
243
- "2011_wiosna": 30.808080808080806,
244
- "2012_jesień": 34.69387755102041,
245
- "2011_jesień": 30.808080808080806,
246
- "2009_jesień": 35.5,
247
- "2022_wiosna": 34.84848484848485,
248
- "2014_wiosna": 26.53061224489796,
249
- "2022_jesien": 34.183673469387756,
250
- "2014_jesien": 35.233160621761655,
251
- "2024_wiosna": 35.025380710659896,
252
- "2015_wiosna": 33.33333333333333,
253
- "2023_wiosna": 35.35353535353536,
254
- "2021_jesien": 31.818181818181817,
255
- "2015_jesien": 37.89473684210527,
256
- "2023_jesien": 31.28205128205128,
257
- "2021_wiosna": 42.857142857142854,
258
- "2013_wiosna": 38.659793814432994,
259
- "2013_jesien": 39.26701570680628,
260
- "overall_accuracy": 34.04502204687863
261
  },
262
  {
263
  "model_name": "model-mistralai-Mistral-Small-Instruct-2409",
264
- "2008_jesień": 38.38383838383838,
265
- "2012_wiosna": 34.5360824742268,
266
- "2010_jesień": 40.7035175879397,
267
- "2009_wiosna": 44.44444444444444,
268
- "2010_wiosna": 46.5,
269
- "2011_wiosna": 34.84848484848485,
270
- "2012_jesień": 46.42857142857143,
271
- "2011_jesień": 38.88888888888889,
272
- "2009_jesień": 45.0,
273
- "2022_wiosna": 38.88888888888889,
274
- "2014_wiosna": 34.69387755102041,
275
- "2022_jesien": 42.857142857142854,
276
- "2014_jesien": 37.82383419689119,
277
- "2024_wiosna": 44.16243654822335,
278
- "2015_wiosna": 38.17204301075269,
279
- "2023_wiosna": 41.41414141414141,
280
- "2021_jesien": 42.42424242424242,
281
- "2015_jesien": 42.10526315789473,
282
- "2023_jesien": 40.0,
283
- "2021_wiosna": 41.3265306122449,
284
- "2013_wiosna": 43.29896907216495,
285
- "2013_jesien": 44.50261780104712,
286
  "overall_accuracy": 40.98398700394523
287
  },
288
  {
289
- "model_name": "model-gpt-4o-2024-08-06",
290
- "2008_jesień": 78.78787878787878,
291
- "2012_wiosna": 77.83505154639175,
292
- "2010_jesień": 74.37185929648241,
293
- "2009_wiosna": 85.85858585858585,
294
- "2010_wiosna": 83.0,
295
- "2011_wiosna": 72.22222222222221,
296
- "2012_jesień": 76.53061224489795,
297
- "2011_jesień": 72.72727272727273,
298
- "2009_jesień": 81.5,
299
- "2022_wiosna": 77.27272727272727,
300
- "2014_wiosna": 79.08163265306123,
301
- "2022_jesien": 69.38775510204081,
302
- "2014_jesien": 77.2020725388601,
303
- "2024_wiosna": 70.55837563451777,
304
- "2015_wiosna": 72.04301075268818,
305
- "2023_wiosna": 72.72727272727273,
306
- "2021_jesien": 72.22222222222221,
307
- "2015_jesien": 75.78947368421053,
308
- "2023_jesien": 69.74358974358974,
309
- "2021_wiosna": 73.9795918367347,
310
- "2013_wiosna": 76.28865979381443,
311
- "2013_jesien": 74.3455497382199,
312
- "overall_accuracy": 75.63239730796009
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
313
  },
314
  {
315
  "model_name": "model-speakleash-Bielik-11B-v2.2-Instruct",
316
- "2008_jesień": 45.45454545454545,
317
- "2012_wiosna": 46.391752577319586,
318
- "2010_jesień": 52.26130653266332,
319
- "2009_wiosna": 51.515151515151516,
320
- "2010_wiosna": 48.5,
321
- "2011_wiosna": 41.91919191919192,
322
- "2012_jesień": 57.6530612244898,
323
- "2011_jesień": 45.95959595959596,
324
- "2009_jesień": 49.5,
325
- "2022_wiosna": 40.4040404040404,
326
- "2014_wiosna": 34.69387755102041,
327
- "2022_jesien": 43.36734693877551,
328
- "2014_jesien": 44.04145077720207,
329
- "2024_wiosna": 50.76142131979695,
330
- "2015_wiosna": 43.54838709677419,
331
- "2023_wiosna": 41.91919191919192,
332
- "2021_jesien": 43.93939393939394,
333
- "2015_jesien": 40.0,
334
- "2023_jesien": 37.94871794871795,
335
- "2021_wiosna": 50.0,
336
- "2013_wiosna": 47.93814432989691,
337
- "2013_jesien": 42.93193717277487,
338
  "overall_accuracy": 45.50939893246693
339
  },
340
  {
341
- "model_name": "model-meta-llama-Llama-3.2-3B-Instruct",
342
- "2008_jesień": 36.36363636363637,
343
- "2012_wiosna": 30.927835051546392,
344
- "2010_jesień": 36.18090452261307,
345
- "2009_wiosna": 34.34343434343434,
346
- "2010_wiosna": 40.5,
347
- "2011_wiosna": 32.82828282828283,
348
- "2012_jesień": 40.816326530612244,
349
- "2011_jesień": 29.292929292929294,
350
- "2009_jesień": 43.0,
351
- "2022_wiosna": 29.797979797979796,
352
- "2014_wiosna": 28.061224489795915,
353
- "2022_jesien": 36.224489795918366,
354
- "2014_jesien": 29.533678756476682,
355
- "2024_wiosna": 35.53299492385787,
356
- "2015_wiosna": 36.55913978494624,
357
- "2023_wiosna": 35.35353535353536,
358
- "2021_jesien": 27.77777777777778,
359
- "2015_jesien": 30.526315789473685,
360
- "2023_jesien": 29.230769230769234,
361
- "2021_wiosna": 31.122448979591837,
362
- "2013_wiosna": 33.50515463917525,
363
- "2013_jesien": 35.07853403141361,
364
- "overall_accuracy": 33.766535158969596
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
365
  },
366
  {
367
  "model_name": "model-Qwen-Qwen2.5-7B-Instruct",
368
- "2008_jesień": 41.41414141414141,
369
- "2012_wiosna": 40.20618556701031,
370
- "2010_jesień": 43.21608040201005,
371
- "2009_wiosna": 40.4040404040404,
372
- "2010_wiosna": 41.5,
373
- "2011_wiosna": 38.38383838383838,
374
- "2012_jesień": 48.97959183673469,
375
- "2011_jesień": 38.88888888888889,
376
- "2009_jesień": 43.5,
377
- "2022_wiosna": 43.93939393939394,
378
- "2014_wiosna": 35.714285714285715,
379
- "2022_jesien": 42.857142857142854,
380
- "2014_jesien": 46.63212435233161,
381
- "2024_wiosna": 45.68527918781726,
382
- "2015_wiosna": 42.473118279569896,
383
- "2023_wiosna": 44.94949494949495,
384
- "2021_jesien": 43.43434343434344,
385
- "2015_jesien": 40.0,
386
- "2023_jesien": 46.15384615384615,
387
- "2021_wiosna": 47.44897959183674,
388
- "2013_wiosna": 44.84536082474227,
389
- "2013_jesien": 43.97905759162304,
390
  "overall_accuracy": 42.93339521930842
391
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
392
  {
393
  "model_name": "model-johnsnowlabs-JSL-MedLlama-3-8B-v2.0",
394
- "2008_jesień": 29.292929292929294,
395
- "2012_wiosna": 31.958762886597935,
396
- "2010_jesień": 28.14070351758794,
397
- "2009_wiosna": 31.313131313131315,
398
- "2010_wiosna": 35.0,
399
- "2011_wiosna": 23.737373737373737,
400
- "2012_jesień": 38.265306122448976,
401
- "2011_jesień": 25.757575757575758,
402
- "2009_jesień": 35.0,
403
- "2022_wiosna": 30.808080808080806,
404
- "2014_wiosna": 31.122448979591837,
405
- "2022_jesien": 34.69387755102041,
406
- "2014_jesien": 34.196891191709845,
407
- "2024_wiosna": 29.949238578680205,
408
- "2015_wiosna": 31.182795698924732,
409
- "2023_wiosna": 30.808080808080806,
410
- "2021_jesien": 29.797979797979796,
411
- "2015_jesien": 26.31578947368421,
412
- "2023_jesien": 32.82051282051282,
413
- "2021_wiosna": 33.6734693877551,
414
- "2013_wiosna": 30.927835051546392,
415
- "2013_jesien": 30.89005235602094,
416
  "overall_accuracy": 31.16732420515201
417
  },
418
  {
419
  "model_name": "model-BioMistral-BioMistral-7B",
420
- "2008_jesień": 23.232323232323232,
421
- "2012_wiosna": 21.1340206185567,
422
- "2010_jesień": 23.115577889447238,
423
- "2009_wiosna": 25.757575757575758,
424
- "2010_wiosna": 23.0,
425
- "2011_wiosna": 23.737373737373737,
426
- "2012_jesień": 28.57142857142857,
427
- "2011_jesień": 24.242424242424242,
428
- "2009_jesień": 23.5,
429
- "2022_wiosna": 20.2020202020202,
430
- "2014_wiosna": 24.489795918367346,
431
- "2022_jesien": 28.57142857142857,
432
- "2014_jesien": 22.279792746113987,
433
- "2024_wiosna": 25.888324873096447,
434
- "2015_wiosna": 24.731182795698924,
435
- "2023_wiosna": 24.747474747474747,
436
- "2021_jesien": 26.767676767676768,
437
- "2015_jesien": 28.421052631578945,
438
- "2023_jesien": 25.64102564102564,
439
- "2021_wiosna": 19.387755102040817,
440
- "2013_wiosna": 23.711340206185564,
441
- "2013_jesien": 29.84293193717277,
442
  "overall_accuracy": 24.576467857971686
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
443
  }
444
  ]
 
1
  [
2
  {
3
+ "model_name": "model-mistralai-Mistral-Large-Instruct-2407",
4
+ "2008 Falĺ": 61.61616161616161,
5
+ "2012 Spring": 54.123711340206185,
6
+ "2010 Falĺ": 62.311557788944725,
7
+ "2009 Spring": 67.67676767676768,
8
+ "2010 Spring": 69.5,
9
+ "2011 Spring": 56.56565656565656,
10
+ "2012 Falĺ": 66.3265306122449,
11
+ "2011 Falĺ": 58.080808080808076,
12
+ "2009 Falĺ": 63.0,
13
+ "2022 Spring": 54.54545454545454,
14
+ "2014 Spring": 54.08163265306123,
15
+ "2022 Fall": 56.63265306122449,
16
+ "2014 Fall": 56.476683937823836,
17
+ "2024 Spring": 55.83756345177665,
18
+ "2015 Spring": 58.602150537634415,
19
+ "2023 Spring": 57.57575757575758,
20
+ "2021 Fall": 56.060606060606055,
21
+ "2015 Fall": 60.0,
22
+ "2023 Fall": 48.205128205128204,
23
+ "2021 Spring": 57.14285714285714,
24
+ "2013 Spring": 61.34020618556701,
25
+ "2013 Fall": 55.497382198952884,
26
+ "overall_accuracy": 58.71431886748666
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  },
28
  {
29
  "model_name": "model-Qwen-Qwen2.5-72B-Instruct",
30
+ "2008 Falĺ": 58.58585858585859,
31
+ "2012 Spring": 56.70103092783505,
32
+ "2010 Falĺ": 60.80402010050251,
33
+ "2009 Spring": 60.1010101010101,
34
+ "2010 Spring": 63.5,
35
+ "2011 Spring": 58.58585858585859,
36
+ "2012 Falĺ": 66.83673469387756,
37
+ "2011 Falĺ": 54.54545454545454,
38
+ "2009 Falĺ": 70.5,
39
+ "2022 Spring": 59.59595959595959,
40
+ "2014 Spring": 53.57142857142857,
41
+ "2022 Fall": 61.73469387755102,
42
+ "2014 Fall": 61.6580310880829,
43
+ "2024 Spring": 57.360406091370564,
44
+ "2015 Spring": 58.602150537634415,
45
+ "2023 Spring": 56.56565656565656,
46
+ "2021 Fall": 59.59595959595959,
47
+ "2015 Fall": 57.36842105263158,
48
+ "2023 Fall": 54.871794871794876,
49
+ "2021 Spring": 58.673469387755105,
50
+ "2013 Spring": 61.855670103092784,
51
+ "2013 Fall": 57.06806282722513,
52
  "overall_accuracy": 59.503365049895564
53
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  {
55
  "model_name": "model-OpenMeditron-Meditron3-8B",
56
+ "2008 Falĺ": 38.88888888888889,
57
+ "2012 Spring": 39.69072164948454,
58
+ "2010 Falĺ": 36.18090452261307,
59
+ "2009 Spring": 41.41414141414141,
60
+ "2010 Spring": 43.0,
61
+ "2011 Spring": 32.82828282828283,
62
+ "2012 Falĺ": 42.3469387755102,
63
+ "2011 Falĺ": 33.33333333333333,
64
+ "2009 Falĺ": 41.5,
65
+ "2022 Spring": 34.34343434343434,
66
+ "2014 Spring": 30.102040816326532,
67
+ "2022 Fall": 36.734693877551024,
68
+ "2014 Fall": 39.89637305699482,
69
+ "2024 Spring": 38.07106598984771,
70
+ "2015 Spring": 36.55913978494624,
71
+ "2023 Spring": 38.38383838383838,
72
+ "2021 Fall": 41.41414141414141,
73
+ "2015 Fall": 39.473684210526315,
74
+ "2023 Fall": 34.35897435897436,
75
+ "2021 Spring": 40.816326530612244,
76
+ "2013 Spring": 42.78350515463917,
77
+ "2013 Fall": 40.83769633507853,
78
  "overall_accuracy": 38.31515432815038
79
  },
80
  {
81
+ "model_name": "model-gpt-4o-2024-08-06",
82
+ "2008 Falĺ": 78.78787878787878,
83
+ "2012 Spring": 77.83505154639175,
84
+ "2010 Falĺ": 74.37185929648241,
85
+ "2009 Spring": 85.85858585858585,
86
+ "2010 Spring": 83.0,
87
+ "2011 Spring": 72.22222222222221,
88
+ "2012 Falĺ": 76.53061224489795,
89
+ "2011 Falĺ": 72.72727272727273,
90
+ "2009 Falĺ": 81.5,
91
+ "2022 Spring": 77.27272727272727,
92
+ "2014 Spring": 79.08163265306123,
93
+ "2022 Fall": 69.38775510204081,
94
+ "2014 Fall": 77.2020725388601,
95
+ "2024 Spring": 70.55837563451777,
96
+ "2015 Spring": 72.04301075268818,
97
+ "2023 Spring": 72.72727272727273,
98
+ "2021 Fall": 72.22222222222221,
99
+ "2015 Fall": 75.78947368421053,
100
+ "2023 Fall": 69.74358974358974,
101
+ "2021 Spring": 73.9795918367347,
102
+ "2013 Spring": 76.28865979381443,
103
+ "2013 Fall": 74.3455497382199,
104
+ "overall_accuracy": 75.63239730796009
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  },
106
  {
107
+ "model_name": "model-meta-llama-Llama-3.2-3B-Instruct",
108
+ "2008 Falĺ": 36.36363636363637,
109
+ "2012 Spring": 30.927835051546392,
110
+ "2010 Falĺ": 36.18090452261307,
111
+ "2009 Spring": 34.34343434343434,
112
+ "2010 Spring": 40.5,
113
+ "2011 Spring": 32.82828282828283,
114
+ "2012 Falĺ": 40.816326530612244,
115
+ "2011 Falĺ": 29.292929292929294,
116
+ "2009 Falĺ": 43.0,
117
+ "2022 Spring": 29.797979797979796,
118
+ "2014 Spring": 28.061224489795915,
119
+ "2022 Fall": 36.224489795918366,
120
+ "2014 Fall": 29.533678756476682,
121
+ "2024 Spring": 35.53299492385787,
122
+ "2015 Spring": 36.55913978494624,
123
+ "2023 Spring": 35.35353535353536,
124
+ "2021 Fall": 27.77777777777778,
125
+ "2015 Fall": 30.526315789473685,
126
+ "2023 Fall": 29.230769230769234,
127
+ "2021 Spring": 31.122448979591837,
128
+ "2013 Spring": 33.50515463917525,
129
+ "2013 Fall": 35.07853403141361,
130
+ "overall_accuracy": 33.766535158969596
131
  },
132
  {
133
  "model_name": "model-mistralai-Mistral-Small-Instruct-2409",
134
+ "2008 Falĺ": 38.38383838383838,
135
+ "2012 Spring": 34.5360824742268,
136
+ "2010 Falĺ": 40.7035175879397,
137
+ "2009 Spring": 44.44444444444444,
138
+ "2010 Spring": 46.5,
139
+ "2011 Spring": 34.84848484848485,
140
+ "2012 Falĺ": 46.42857142857143,
141
+ "2011 Falĺ": 38.88888888888889,
142
+ "2009 Falĺ": 45.0,
143
+ "2022 Spring": 38.88888888888889,
144
+ "2014 Spring": 34.69387755102041,
145
+ "2022 Fall": 42.857142857142854,
146
+ "2014 Fall": 37.82383419689119,
147
+ "2024 Spring": 44.16243654822335,
148
+ "2015 Spring": 38.17204301075269,
149
+ "2023 Spring": 41.41414141414141,
150
+ "2021 Fall": 42.42424242424242,
151
+ "2015 Fall": 42.10526315789473,
152
+ "2023 Fall": 40.0,
153
+ "2021 Spring": 41.3265306122449,
154
+ "2013 Spring": 43.29896907216495,
155
+ "2013 Fall": 44.50261780104712,
156
  "overall_accuracy": 40.98398700394523
157
  },
158
  {
159
+ "model_name": "model-gpt-4o-mini-2024-07-18",
160
+ "2008 Falĺ": 59.09090909090909,
161
+ "2012 Spring": 55.670103092783506,
162
+ "2010 Falĺ": 55.27638190954774,
163
+ "2009 Spring": 68.18181818181817,
164
+ "2010 Spring": 62.5,
165
+ "2011 Spring": 50.0,
166
+ "2012 Falĺ": 65.3061224489796,
167
+ "2011 Falĺ": 55.05050505050505,
168
+ "2009 Falĺ": 64.0,
169
+ "2022 Spring": 52.52525252525253,
170
+ "2014 Spring": 46.93877551020408,
171
+ "2022 Fall": 54.08163265306123,
172
+ "2014 Fall": 57.51295336787565,
173
+ "2024 Spring": 56.34517766497462,
174
+ "2015 Spring": 52.68817204301075,
175
+ "2023 Spring": 53.535353535353536,
176
+ "2021 Fall": 58.080808080808076,
177
+ "2015 Fall": 57.89473684210527,
178
+ "2023 Fall": 58.46153846153847,
179
+ "2021 Spring": 59.693877551020414,
180
+ "2013 Spring": 55.154639175257735,
181
+ "2013 Fall": 51.30890052356021,
182
+ "overall_accuracy": 56.811325133441635
183
+ },
184
+ {
185
+ "model_name": "model-meta-llama-Llama-3.2-1B-Instruct",
186
+ "2008 Falĺ": 24.242424242424242,
187
+ "2012 Spring": 20.618556701030926,
188
+ "2010 Falĺ": 23.618090452261306,
189
+ "2009 Spring": 24.242424242424242,
190
+ "2010 Spring": 23.0,
191
+ "2011 Spring": 24.747474747474747,
192
+ "2012 Falĺ": 28.57142857142857,
193
+ "2011 Falĺ": 21.71717171717172,
194
+ "2009 Falĺ": 25.5,
195
+ "2022 Spring": 21.21212121212121,
196
+ "2014 Spring": 22.448979591836736,
197
+ "2022 Fall": 29.591836734693878,
198
+ "2014 Fall": 23.316062176165804,
199
+ "2024 Spring": 33.50253807106599,
200
+ "2015 Spring": 23.655913978494624,
201
+ "2023 Spring": 28.28282828282828,
202
+ "2021 Fall": 27.27272727272727,
203
+ "2015 Fall": 24.736842105263158,
204
+ "2023 Fall": 27.692307692307693,
205
+ "2021 Spring": 22.448979591836736,
206
+ "2013 Spring": 23.711340206185564,
207
+ "2013 Fall": 27.748691099476442,
208
+ "overall_accuracy": 25.08702715247157
209
  },
210
  {
211
  "model_name": "model-speakleash-Bielik-11B-v2.2-Instruct",
212
+ "2008 Falĺ": 45.45454545454545,
213
+ "2012 Spring": 46.391752577319586,
214
+ "2010 Falĺ": 52.26130653266332,
215
+ "2009 Spring": 51.515151515151516,
216
+ "2010 Spring": 48.5,
217
+ "2011 Spring": 41.91919191919192,
218
+ "2012 Falĺ": 57.6530612244898,
219
+ "2011 Falĺ": 45.95959595959596,
220
+ "2009 Falĺ": 49.5,
221
+ "2022 Spring": 40.4040404040404,
222
+ "2014 Spring": 34.69387755102041,
223
+ "2022 Fall": 43.36734693877551,
224
+ "2014 Fall": 44.04145077720207,
225
+ "2024 Spring": 50.76142131979695,
226
+ "2015 Spring": 43.54838709677419,
227
+ "2023 Spring": 41.91919191919192,
228
+ "2021 Fall": 43.93939393939394,
229
+ "2015 Fall": 40.0,
230
+ "2023 Fall": 37.94871794871795,
231
+ "2021 Spring": 50.0,
232
+ "2013 Spring": 47.93814432989691,
233
+ "2013 Fall": 42.93193717277487,
234
  "overall_accuracy": 45.50939893246693
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 Falĺ": 19.19191919191919,
265
+ "2012 Spring": 19.072164948453608,
266
+ "2010 Falĺ": 35.175879396984925,
267
+ "2009 Spring": 50.0,
268
+ "2010 Spring": 43.0,
269
+ "2011 Spring": 38.88888888888889,
270
+ "2012 Falĺ": 43.36734693877551,
271
+ "2011 Falĺ": 35.35353535353536,
272
+ "2009 Falĺ": 48.0,
273
+ "2022 Spring": 45.95959595959596,
274
+ "2014 Spring": 39.285714285714285,
275
+ "2022 Fall": 43.36734693877551,
276
+ "2014 Fall": 39.37823834196891,
277
+ "2024 Spring": 44.16243654822335,
278
+ "2015 Spring": 41.39784946236559,
279
+ "2023 Spring": 42.92929292929293,
280
+ "2021 Fall": 42.92929292929293,
281
+ "2015 Fall": 38.421052631578945,
282
+ "2023 Fall": 38.97435897435898,
283
+ "2021 Spring": 41.83673469387755,
284
+ "2013 Spring": 41.23711340206185,
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 Falĺ": 62.121212121212125,
317
+ "2012 Spring": 61.34020618556701,
318
+ "2010 Falĺ": 62.8140703517588,
319
+ "2009 Spring": 69.1919191919192,
320
+ "2010 Spring": 73.0,
321
+ "2011 Spring": 59.59595959595959,
322
+ "2012 Falĺ": 69.89795918367348,
323
+ "2011 Falĺ": 65.65656565656566,
324
+ "2009 Falĺ": 68.0,
325
+ "2022 Spring": 68.68686868686868,
326
+ "2014 Spring": 54.59183673469388,
327
+ "2022 Fall": 62.755102040816325,
328
+ "2014 Fall": 60.62176165803109,
329
+ "2024 Spring": 61.42131979695431,
330
+ "2015 Spring": 60.215053763440864,
331
+ "2023 Spring": 62.62626262626263,
332
+ "2021 Fall": 64.14141414141415,
333
+ "2015 Fall": 58.42105263157895,
334
+ "2023 Fall": 61.02564102564103,
335
+ "2021 Spring": 68.36734693877551,
336
+ "2013 Spring": 62.371134020618555,
337
+ "2013 Fall": 57.06806282722513,
338
+ "overall_accuracy": 63.402181480621955
339
+ },
340
  {
341
  "model_name": "model-johnsnowlabs-JSL-MedLlama-3-8B-v2.0",
342
+ "2008 Falĺ": 29.292929292929294,
343
+ "2012 Spring": 31.958762886597935,
344
+ "2010 Falĺ": 28.14070351758794,
345
+ "2009 Spring": 31.313131313131315,
346
+ "2010 Spring": 35.0,
347
+ "2011 Spring": 23.737373737373737,
348
+ "2012 Falĺ": 38.265306122448976,
349
+ "2011 Falĺ": 25.757575757575758,
350
+ "2009 Falĺ": 35.0,
351
+ "2022 Spring": 30.808080808080806,
352
+ "2014 Spring": 31.122448979591837,
353
+ "2022 Fall": 34.69387755102041,
354
+ "2014 Fall": 34.196891191709845,
355
+ "2024 Spring": 29.949238578680205,
356
+ "2015 Spring": 31.182795698924732,
357
+ "2023 Spring": 30.808080808080806,
358
+ "2021 Fall": 29.797979797979796,
359
+ "2015 Fall": 26.31578947368421,
360
+ "2023 Fall": 32.82051282051282,
361
+ "2021 Spring": 33.6734693877551,
362
+ "2013 Spring": 30.927835051546392,
363
+ "2013 Fall": 30.89005235602094,
364
  "overall_accuracy": 31.16732420515201
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 Falĺ": 30.303030303030305,
395
+ "2012 Spring": 31.958762886597935,
396
+ "2010 Falĺ": 30.15075376884422,
397
+ "2009 Spring": 37.37373737373738,
398
+ "2010 Spring": 31.5,
399
+ "2011 Spring": 30.808080808080806,
400
+ "2012 Falĺ": 34.69387755102041,
401
+ "2011 Falĺ": 30.808080808080806,
402
+ "2009 Falĺ": 35.5,
403
+ "2022 Spring": 34.84848484848485,
404
+ "2014 Spring": 26.53061224489796,
405
+ "2022 Fall": 34.183673469387756,
406
+ "2014 Fall": 35.233160621761655,
407
+ "2024 Spring": 35.025380710659896,
408
+ "2015 Spring": 33.33333333333333,
409
+ "2023 Spring": 35.35353535353536,
410
+ "2021 Fall": 31.818181818181817,
411
+ "2015 Fall": 37.89473684210527,
412
+ "2023 Fall": 31.28205128205128,
413
+ "2021 Spring": 42.857142857142854,
414
+ "2013 Spring": 38.659793814432994,
415
+ "2013 Fall": 39.26701570680628,
416
+ "overall_accuracy": 34.04502204687863
417
+ },
418
+ {
419
+ "model_name": "model-OpenMeditron-Meditron3-70B",
420
+ "2008 Falĺ": 45.95959595959596,
421
+ "2012 Spring": 43.29896907216495,
422
+ "2010 Falĺ": 46.733668341708544,
423
+ "2009 Spring": 51.010101010101,
424
+ "2010 Spring": 49.0,
425
+ "2011 Spring": 42.42424242424242,
426
+ "2012 Falĺ": 47.44897959183674,
427
+ "2011 Falĺ": 46.96969696969697,
428
+ "2009 Falĺ": 49.0,
429
+ "2022 Spring": 45.95959595959596,
430
+ "2014 Spring": 41.83673469387755,
431
+ "2022 Fall": 48.46938775510204,
432
+ "2014 Fall": 47.15025906735752,
433
+ "2024 Spring": 52.28426395939086,
434
+ "2015 Spring": 50.53763440860215,
435
+ "2023 Spring": 47.474747474747474,
436
+ "2021 Fall": 48.98989898989899,
437
+ "2015 Fall": 51.05263157894737,
438
+ "2023 Fall": 42.56410256410256,
439
+ "2021 Spring": 45.40816326530612,
440
+ "2013 Spring": 49.48453608247423,
441
+ "2013 Fall": 45.54973821989529,
442
+ "overall_accuracy": 47.203527500580186
443
  }
444
  ]
leaderboards/lek_accs.json CHANGED
@@ -1,444 +1,444 @@
1
  [
2
  {
3
- "model_name": "model-meta-llama-Meta-Llama-3.1-8B-Instruct",
4
- "2011_wiosna": 53.03030303030303,
5
- "2010_wiosna": 54.0,
6
- "2008_jesień": 51.26903553299492,
7
- "2011_jesień": 56.56565656565656,
8
- "2009_jesień": 47.20812182741117,
9
- "2010_jesień": 43.43434343434344,
10
- "2012_wiosna": 53.0,
11
- "2009_wiosna": 45.22613065326633,
12
- "2012_jesień": 52.55102040816326,
13
- "2022_wiosna": 45.91836734693878,
14
- "2014_wiosna": 52.307692307692314,
15
- "2022_jesien": 53.06122448979592,
16
- "2014_jesien": 53.125,
17
- "2024_wiosna": 57.868020304568525,
18
- "2015_wiosna": 54.54545454545454,
19
- "2023_wiosna": 51.03092783505154,
20
- "2021_jesien": 52.0618556701031,
21
- "2015_jesien": 44.73684210526316,
22
- "2023_jesien": 48.45360824742268,
23
- "2021_wiosna": 47.0,
24
- "2013_wiosna": 54.166666666666664,
25
- "2013_jesien": 51.832460732984295,
26
- "overall_accuracy": 51.02040816326531
27
  },
28
  {
29
- "model_name": "model-meta-llama-Meta-Llama-3.1-70B-Instruct",
30
- "2011_wiosna": 77.27272727272727,
31
- "2010_wiosna": 82.0,
32
- "2008_jesień": 79.69543147208121,
33
- "2011_jesień": 83.33333333333334,
34
- "2009_jesień": 81.21827411167513,
35
- "2010_jesień": 80.8080808080808,
36
- "2012_wiosna": 80.0,
37
- "2009_wiosna": 72.8643216080402,
38
- "2012_jesień": 81.12244897959184,
39
- "2022_wiosna": 79.59183673469387,
40
- "2014_wiosna": 76.41025641025641,
41
- "2022_jesien": 82.14285714285714,
42
- "2014_jesien": 87.5,
43
- "2024_wiosna": 86.29441624365482,
44
- "2015_wiosna": 77.77777777777779,
45
- "2023_wiosna": 78.8659793814433,
46
- "2021_jesien": 81.44329896907216,
47
- "2015_jesien": 78.42105263157895,
48
- "2023_jesien": 83.50515463917526,
49
- "2021_wiosna": 84.5,
50
- "2013_wiosna": 77.60416666666666,
51
- "2013_jesien": 78.01047120418848,
52
- "overall_accuracy": 80.47309833024119
53
  },
54
  {
55
  "model_name": "model-Qwen-Qwen2.5-72B-Instruct",
56
- "2011_wiosna": 75.25252525252525,
57
- "2010_wiosna": 76.0,
58
- "2008_jesień": 80.71065989847716,
59
- "2011_jesień": 73.73737373737373,
60
- "2009_jesień": 71.06598984771574,
61
- "2010_jesień": 74.74747474747475,
62
- "2012_wiosna": 79.0,
63
- "2009_wiosna": 74.87437185929649,
64
- "2012_jesień": 76.0204081632653,
65
- "2022_wiosna": 72.95918367346938,
66
- "2014_wiosna": 77.43589743589745,
67
- "2022_jesien": 77.04081632653062,
68
- "2014_jesien": 84.375,
69
- "2024_wiosna": 81.21827411167513,
70
- "2015_wiosna": 75.25252525252525,
71
- "2023_wiosna": 77.83505154639175,
72
- "2021_jesien": 73.19587628865979,
73
- "2015_jesien": 73.15789473684211,
74
- "2023_jesien": 76.28865979381443,
75
- "2021_wiosna": 78.5,
76
- "2013_wiosna": 72.91666666666666,
77
- "2013_jesien": 79.05759162303664,
78
  "overall_accuracy": 76.39146567717997
79
  },
80
- {
81
- "model_name": "model-gpt-4o-mini-2024-07-18",
82
- "2011_wiosna": 75.75757575757575,
83
- "2010_wiosna": 74.5,
84
- "2008_jesień": 77.15736040609137,
85
- "2011_jesień": 72.72727272727273,
86
- "2009_jesień": 71.06598984771574,
87
- "2010_jesień": 75.75757575757575,
88
- "2012_wiosna": 75.0,
89
- "2009_wiosna": 72.8643216080402,
90
- "2012_jesień": 78.57142857142857,
91
- "2022_wiosna": 70.40816326530613,
92
- "2014_wiosna": 72.82051282051282,
93
- "2022_jesien": 76.53061224489795,
94
- "2014_jesien": 76.5625,
95
- "2024_wiosna": 82.23350253807106,
96
- "2015_wiosna": 73.23232323232324,
97
- "2023_wiosna": 75.25773195876289,
98
- "2021_jesien": 72.16494845360825,
99
- "2015_jesien": 75.78947368421053,
100
- "2023_jesien": 78.35051546391753,
101
- "2021_wiosna": 80.5,
102
- "2013_wiosna": 74.47916666666666,
103
- "2013_jesien": 78.01047120418848,
104
- "overall_accuracy": 75.44063079777365
105
- },
106
- {
107
- "model_name": "model-aaditya-Llama3-OpenBioLLM-70B",
108
- "2011_wiosna": 23.232323232323232,
109
- "2010_wiosna": 18.0,
110
- "2008_jesień": 36.04060913705584,
111
- "2011_jesień": 58.58585858585859,
112
- "2009_jesień": 54.314720812182735,
113
- "2010_jesień": 54.04040404040404,
114
- "2012_wiosna": 61.0,
115
- "2009_wiosna": 54.2713567839196,
116
- "2012_jesień": 58.16326530612245,
117
- "2022_wiosna": 60.204081632653065,
118
- "2014_wiosna": 57.43589743589743,
119
- "2022_jesien": 57.6530612244898,
120
- "2014_jesien": 63.541666666666664,
121
- "2024_wiosna": 68.02030456852792,
122
- "2015_wiosna": 62.121212121212125,
123
- "2023_wiosna": 62.371134020618555,
124
- "2021_jesien": 61.34020618556701,
125
- "2015_jesien": 57.89473684210527,
126
- "2023_jesien": 62.371134020618555,
127
- "2021_wiosna": 65.0,
128
- "2013_wiosna": 57.8125,
129
- "2013_jesien": 61.25654450261781,
130
- "overall_accuracy": 55.14842300556586
131
- },
132
- {
133
- "model_name": "model-mistralai-Mistral-Large-Instruct-2407",
134
- "2011_wiosna": 76.26262626262627,
135
- "2010_wiosna": 76.5,
136
- "2008_jesień": 76.6497461928934,
137
- "2011_jesień": 79.29292929292929,
138
- "2009_jesień": 71.57360406091371,
139
- "2010_jesień": 74.24242424242425,
140
- "2012_wiosna": 77.5,
141
- "2009_wiosna": 72.8643216080402,
142
- "2012_jesień": 76.53061224489795,
143
- "2022_wiosna": 72.95918367346938,
144
- "2014_wiosna": 80.0,
145
- "2022_jesien": 75.0,
146
- "2014_jesien": 76.5625,
147
- "2024_wiosna": 86.80203045685279,
148
- "2015_wiosna": 75.25252525252525,
149
- "2023_wiosna": 79.38144329896907,
150
- "2021_jesien": 76.28865979381443,
151
- "2015_jesien": 71.05263157894737,
152
- "2023_jesien": 76.80412371134021,
153
- "2021_wiosna": 79.5,
154
- "2013_wiosna": 71.875,
155
- "2013_jesien": 75.91623036649214,
156
- "overall_accuracy": 76.32189239332097
157
- },
158
  {
159
  "model_name": "model-OpenMeditron-Meditron3-8B",
160
- "2011_wiosna": 43.93939393939394,
161
- "2010_wiosna": 48.0,
162
- "2008_jesień": 46.192893401015226,
163
- "2011_jesień": 47.474747474747474,
164
- "2009_jesień": 46.7005076142132,
165
- "2010_jesień": 40.4040404040404,
166
- "2012_wiosna": 43.5,
167
- "2009_wiosna": 43.21608040201005,
168
- "2012_jesień": 45.40816326530612,
169
- "2022_wiosna": 41.83673469387755,
170
- "2014_wiosna": 42.05128205128205,
171
- "2022_jesien": 43.36734693877551,
172
- "2014_jesien": 52.604166666666664,
173
- "2024_wiosna": 51.26903553299492,
174
- "2015_wiosna": 44.94949494949495,
175
- "2023_wiosna": 47.93814432989691,
176
- "2021_jesien": 44.329896907216494,
177
- "2015_jesien": 42.63157894736842,
178
- "2023_jesien": 42.2680412371134,
179
- "2021_wiosna": 44.0,
180
- "2013_wiosna": 48.95833333333333,
181
- "2013_jesien": 51.832460732984295,
182
  "overall_accuracy": 45.570500927643785
183
  },
184
  {
185
- "model_name": "model-meta-llama-Llama-3.2-1B-Instruct",
186
- "2011_wiosna": 18.181818181818183,
187
- "2010_wiosna": 25.5,
188
- "2008_jesień": 20.304568527918782,
189
- "2011_jesień": 30.303030303030305,
190
- "2009_jesień": 25.380710659898476,
191
- "2010_jesień": 23.737373737373737,
192
- "2012_wiosna": 29.5,
193
- "2009_wiosna": 29.145728643216078,
194
- "2012_jesień": 26.53061224489796,
195
- "2022_wiosna": 20.918367346938776,
196
- "2014_wiosna": 25.64102564102564,
197
- "2022_jesien": 23.46938775510204,
198
- "2014_jesien": 26.041666666666668,
199
- "2024_wiosna": 25.380710659898476,
200
- "2015_wiosna": 26.767676767676768,
201
- "2023_wiosna": 22.68041237113402,
202
- "2021_jesien": 23.195876288659793,
203
- "2015_jesien": 23.684210526315788,
204
- "2023_jesien": 27.835051546391753,
205
- "2021_wiosna": 26.5,
206
- "2013_wiosna": 21.875,
207
- "2013_jesien": 23.036649214659686,
208
- "overall_accuracy": 24.81447124304267
209
- },
210
- {
211
- "model_name": "model-OpenMeditron-Meditron3-70B",
212
- "2011_wiosna": 64.14141414141415,
213
- "2010_wiosna": 73.5,
214
- "2008_jesień": 62.43654822335025,
215
- "2011_jesień": 69.1919191919192,
216
- "2009_jesień": 58.88324873096447,
217
- "2010_jesień": 61.111111111111114,
218
- "2012_wiosna": 68.5,
219
- "2009_wiosna": 59.2964824120603,
220
- "2012_jesień": 66.83673469387756,
221
- "2022_wiosna": 70.91836734693877,
222
- "2014_wiosna": 70.25641025641025,
223
- "2022_jesien": 63.775510204081634,
224
- "2014_jesien": 69.27083333333334,
225
- "2024_wiosna": 77.66497461928934,
226
- "2015_wiosna": 67.67676767676768,
227
- "2023_wiosna": 67.0103092783505,
228
- "2021_jesien": 64.43298969072166,
229
- "2015_jesien": 66.3157894736842,
230
- "2023_jesien": 68.55670103092784,
231
- "2021_wiosna": 70.5,
232
- "2013_wiosna": 65.625,
233
- "2013_jesien": 66.49214659685863,
234
- "overall_accuracy": 66.92949907235621
235
- },
236
- {
237
- "model_name": "model-mistralai-Mistral-Small-Instruct-2409",
238
- "2011_wiosna": 46.464646464646464,
239
- "2010_wiosna": 54.0,
240
- "2008_jesień": 51.26903553299492,
241
- "2011_jesień": 52.02020202020202,
242
- "2009_jesień": 45.68527918781726,
243
- "2010_jesień": 50.0,
244
- "2012_wiosna": 56.49999999999999,
245
- "2009_wiosna": 52.26130653266332,
246
- "2012_jesień": 49.48979591836735,
247
- "2022_wiosna": 48.97959183673469,
248
- "2014_wiosna": 48.205128205128204,
249
- "2022_jesien": 52.04081632653062,
250
- "2014_jesien": 48.95833333333333,
251
- "2024_wiosna": 58.37563451776649,
252
- "2015_wiosna": 52.02020202020202,
253
- "2023_wiosna": 53.09278350515464,
254
- "2021_jesien": 53.608247422680414,
255
- "2015_jesien": 47.89473684210526,
256
- "2023_jesien": 52.0618556701031,
257
- "2021_wiosna": 55.00000000000001,
258
- "2013_wiosna": 49.47916666666667,
259
- "2013_jesien": 52.35602094240838,
260
- "overall_accuracy": 51.36827458256029
261
  },
262
  {
263
- "model_name": "model-ProbeMedicalYonseiMAILab-medllama3-v20",
264
- "2011_wiosna": 39.8989898989899,
265
- "2010_wiosna": 46.0,
266
- "2008_jesień": 38.07106598984771,
267
- "2011_jesień": 40.4040404040404,
268
- "2009_jesień": 36.04060913705584,
269
- "2010_jesień": 38.38383838383838,
270
- "2012_wiosna": 40.5,
271
- "2009_wiosna": 35.678391959798994,
272
- "2012_jesień": 46.42857142857143,
273
- "2022_wiosna": 39.285714285714285,
274
- "2014_wiosna": 37.94871794871795,
275
- "2022_jesien": 41.83673469387755,
276
- "2014_jesien": 43.75,
277
- "2024_wiosna": 44.67005076142132,
278
- "2015_wiosna": 38.38383838383838,
279
- "2023_wiosna": 41.23711340206185,
280
- "2021_jesien": 45.36082474226804,
281
- "2015_jesien": 32.631578947368425,
282
- "2023_jesien": 44.84536082474227,
283
- "2021_wiosna": 40.5,
284
- "2013_wiosna": 41.14583333333333,
285
- "2013_jesien": 40.31413612565445,
286
- "overall_accuracy": 40.60760667903525
287
  },
288
  {
289
- "model_name": "model-gpt-4o-2024-08-06",
290
- "2011_wiosna": 87.37373737373737,
291
- "2010_wiosna": 88.5,
292
- "2008_jesień": 88.3248730964467,
293
- "2011_jesień": 90.40404040404042,
294
- "2009_jesień": 87.81725888324873,
295
- "2010_jesień": 89.39393939393939,
296
- "2012_wiosna": 90.0,
297
- "2009_wiosna": 86.93467336683418,
298
- "2012_jesień": 88.77551020408163,
299
- "2022_wiosna": 89.28571428571429,
300
- "2014_wiosna": 88.71794871794872,
301
- "2022_jesien": 91.3265306122449,
302
- "2014_jesien": 91.66666666666666,
303
- "2024_wiosna": 93.4010152284264,
304
- "2015_wiosna": 89.8989898989899,
305
- "2023_wiosna": 90.72164948453609,
306
- "2021_jesien": 86.5979381443299,
307
- "2015_jesien": 87.89473684210526,
308
- "2023_jesien": 91.23711340206185,
309
- "2021_wiosna": 91.0,
310
- "2013_wiosna": 89.0625,
311
- "2013_jesien": 88.48167539267016,
312
- "overall_accuracy": 89.40166975881262
313
  },
314
  {
315
  "model_name": "model-speakleash-Bielik-11B-v2.2-Instruct",
316
- "2011_wiosna": 59.59595959595959,
317
- "2010_wiosna": 62.0,
318
- "2008_jesień": 59.89847715736041,
319
- "2011_jesień": 60.1010101010101,
320
- "2009_jesień": 58.37563451776649,
321
- "2010_jesień": 63.13131313131313,
322
- "2012_wiosna": 61.0,
323
- "2009_wiosna": 63.31658291457286,
324
- "2012_jesień": 63.26530612244898,
325
- "2022_wiosna": 58.16326530612245,
326
- "2014_wiosna": 57.948717948717956,
327
- "2022_jesien": 67.85714285714286,
328
- "2014_jesien": 63.541666666666664,
329
- "2024_wiosna": 65.48223350253807,
330
- "2015_wiosna": 59.59595959595959,
331
- "2023_wiosna": 63.4020618556701,
332
- "2021_jesien": 62.371134020618555,
333
- "2015_jesien": 61.578947368421055,
334
- "2023_jesien": 62.88659793814433,
335
- "2021_wiosna": 64.5,
336
- "2013_wiosna": 61.458333333333336,
337
- "2013_jesien": 61.78010471204188,
338
  "overall_accuracy": 61.87384044526901
339
  },
340
  {
341
- "model_name": "model-meta-llama-Llama-3.2-3B-Instruct",
342
- "2011_wiosna": 36.868686868686865,
343
- "2010_wiosna": 38.0,
344
- "2008_jesień": 38.578680203045685,
345
- "2011_jesień": 47.97979797979798,
346
- "2009_jesień": 38.578680203045685,
347
- "2010_jesień": 38.38383838383838,
348
- "2012_wiosna": 36.0,
349
- "2009_wiosna": 40.20100502512563,
350
- "2012_jesień": 40.30612244897959,
351
- "2022_wiosna": 38.265306122448976,
352
- "2014_wiosna": 37.94871794871795,
353
- "2022_jesien": 38.775510204081634,
354
- "2014_jesien": 36.97916666666667,
355
- "2024_wiosna": 42.63959390862944,
356
- "2015_wiosna": 40.4040404040404,
357
- "2023_wiosna": 37.628865979381445,
358
- "2021_jesien": 42.2680412371134,
359
- "2015_jesien": 34.73684210526316,
360
- "2023_jesien": 42.78350515463917,
361
- "2021_wiosna": 39.0,
362
- "2013_wiosna": 34.375,
363
- "2013_jesien": 43.97905759162304,
364
- "overall_accuracy": 39.308905380333954
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
365
  },
366
  {
367
  "model_name": "model-Qwen-Qwen2.5-7B-Instruct",
368
- "2011_wiosna": 50.0,
369
- "2010_wiosna": 52.5,
370
- "2008_jesień": 54.314720812182735,
371
- "2011_jesień": 59.59595959595959,
372
- "2009_jesień": 45.68527918781726,
373
- "2010_jesień": 48.484848484848484,
374
- "2012_wiosna": 45.0,
375
- "2009_wiosna": 51.75879396984925,
376
- "2012_jesień": 48.97959183673469,
377
- "2022_wiosna": 50.0,
378
- "2014_wiosna": 48.717948717948715,
379
- "2022_jesien": 52.55102040816326,
380
- "2014_jesien": 53.645833333333336,
381
- "2024_wiosna": 55.32994923857868,
382
- "2015_wiosna": 47.474747474747474,
383
- "2023_wiosna": 51.546391752577314,
384
- "2021_jesien": 58.24742268041238,
385
- "2015_jesien": 50.0,
386
- "2023_jesien": 50.0,
387
- "2021_wiosna": 50.5,
388
- "2013_wiosna": 56.770833333333336,
389
- "2013_jesien": 50.26178010471204,
390
  "overall_accuracy": 51.41465677179963
391
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
392
  {
393
  "model_name": "model-johnsnowlabs-JSL-MedLlama-3-8B-v2.0",
394
- "2011_wiosna": 37.37373737373738,
395
- "2010_wiosna": 38.5,
396
- "2008_jesień": 38.07106598984771,
397
- "2011_jesień": 42.92929292929293,
398
- "2009_jesień": 31.979695431472084,
399
- "2010_jesień": 34.84848484848485,
400
- "2012_wiosna": 37.0,
401
- "2009_wiosna": 34.17085427135678,
402
- "2012_jesień": 39.285714285714285,
403
- "2022_wiosna": 34.183673469387756,
404
- "2014_wiosna": 36.92307692307693,
405
- "2022_jesien": 41.83673469387755,
406
- "2014_jesien": 35.9375,
407
- "2024_wiosna": 37.055837563451774,
408
- "2015_wiosna": 33.83838383838384,
409
- "2023_wiosna": 32.98969072164948,
410
- "2021_jesien": 36.597938144329895,
411
- "2015_jesien": 33.1578947368421,
412
- "2023_jesien": 38.659793814432994,
413
- "2021_wiosna": 33.5,
414
- "2013_wiosna": 32.8125,
415
- "2013_jesien": 40.31413612565445,
416
  "overall_accuracy": 36.45640074211503
417
  },
418
  {
419
  "model_name": "model-BioMistral-BioMistral-7B",
420
- "2011_wiosna": 22.727272727272727,
421
- "2010_wiosna": 25.5,
422
- "2008_jesień": 20.812182741116754,
423
- "2011_jesień": 27.77777777777778,
424
- "2009_jesień": 24.36548223350254,
425
- "2010_jesień": 27.27272727272727,
426
- "2012_wiosna": 27.500000000000004,
427
- "2009_wiosna": 28.643216080402013,
428
- "2012_jesień": 22.95918367346939,
429
- "2022_wiosna": 22.95918367346939,
430
- "2014_wiosna": 26.666666666666668,
431
- "2022_jesien": 24.489795918367346,
432
- "2014_jesien": 25.520833333333332,
433
- "2024_wiosna": 28.426395939086298,
434
- "2015_wiosna": 27.77777777777778,
435
- "2023_wiosna": 26.288659793814436,
436
- "2021_jesien": 26.288659793814436,
437
- "2015_jesien": 30.0,
438
- "2023_jesien": 24.742268041237114,
439
- "2021_wiosna": 28.000000000000004,
440
- "2013_wiosna": 27.604166666666668,
441
- "2013_jesien": 22.5130890052356,
442
  "overall_accuracy": 25.858070500927642
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
443
  }
444
  ]
 
1
  [
2
  {
3
+ "model_name": "model-mistralai-Mistral-Large-Instruct-2407",
4
+ "2011 Spring": 76.26262626262627,
5
+ "2010 Spring": 76.5,
6
+ "2008 Falĺ": 76.6497461928934,
7
+ "2011 Falĺ": 79.29292929292929,
8
+ "2009 Falĺ": 71.57360406091371,
9
+ "2010 Falĺ": 74.24242424242425,
10
+ "2012 Spring": 77.5,
11
+ "2009 Spring": 72.8643216080402,
12
+ "2012 Falĺ": 76.53061224489795,
13
+ "2022 Spring": 72.95918367346938,
14
+ "2014 Spring": 80.0,
15
+ "2022 Fall": 75.0,
16
+ "2014 Fall": 76.5625,
17
+ "2024 Spring": 86.80203045685279,
18
+ "2015 Spring": 75.25252525252525,
19
+ "2023 Spring": 79.38144329896907,
20
+ "2021 Fall": 76.28865979381443,
21
+ "2015 Fall": 71.05263157894737,
22
+ "2023 Fall": 76.80412371134021,
23
+ "2021 Spring": 79.5,
24
+ "2013 Spring": 71.875,
25
+ "2013 Fall": 75.91623036649214,
26
+ "overall_accuracy": 76.32189239332097
27
  },
28
  {
29
+ "model_name": "model-gpt-4o-2024-08-06",
30
+ "2011 Spring": 87.37373737373737,
31
+ "2010 Spring": 88.5,
32
+ "2008 Falĺ": 88.3248730964467,
33
+ "2011 Falĺ": 90.40404040404042,
34
+ "2009 Falĺ": 87.81725888324873,
35
+ "2010 Falĺ": 89.39393939393939,
36
+ "2012 Spring": 90.0,
37
+ "2009 Spring": 86.93467336683418,
38
+ "2012 Falĺ": 88.77551020408163,
39
+ "2022 Spring": 89.28571428571429,
40
+ "2014 Spring": 88.71794871794872,
41
+ "2022 Fall": 91.3265306122449,
42
+ "2014 Fall": 91.66666666666666,
43
+ "2024 Spring": 93.4010152284264,
44
+ "2015 Spring": 89.8989898989899,
45
+ "2023 Spring": 90.72164948453609,
46
+ "2021 Fall": 86.5979381443299,
47
+ "2015 Fall": 87.89473684210526,
48
+ "2023 Fall": 91.23711340206185,
49
+ "2021 Spring": 91.0,
50
+ "2013 Spring": 89.0625,
51
+ "2013 Fall": 88.48167539267016,
52
+ "overall_accuracy": 89.40166975881262
53
  },
54
  {
55
  "model_name": "model-Qwen-Qwen2.5-72B-Instruct",
56
+ "2011 Spring": 75.25252525252525,
57
+ "2010 Spring": 76.0,
58
+ "2008 Falĺ": 80.71065989847716,
59
+ "2011 Falĺ": 73.73737373737373,
60
+ "2009 Falĺ": 71.06598984771574,
61
+ "2010 Falĺ": 74.74747474747475,
62
+ "2012 Spring": 79.0,
63
+ "2009 Spring": 74.87437185929649,
64
+ "2012 Falĺ": 76.0204081632653,
65
+ "2022 Spring": 72.95918367346938,
66
+ "2014 Spring": 77.43589743589745,
67
+ "2022 Fall": 77.04081632653062,
68
+ "2014 Fall": 84.375,
69
+ "2024 Spring": 81.21827411167513,
70
+ "2015 Spring": 75.25252525252525,
71
+ "2023 Spring": 77.83505154639175,
72
+ "2021 Fall": 73.19587628865979,
73
+ "2015 Fall": 73.15789473684211,
74
+ "2023 Fall": 76.28865979381443,
75
+ "2021 Spring": 78.5,
76
+ "2013 Spring": 72.91666666666666,
77
+ "2013 Fall": 79.05759162303664,
78
  "overall_accuracy": 76.39146567717997
79
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  {
81
  "model_name": "model-OpenMeditron-Meditron3-8B",
82
+ "2011 Spring": 43.93939393939394,
83
+ "2010 Spring": 48.0,
84
+ "2008 Falĺ": 46.192893401015226,
85
+ "2011 Falĺ": 47.474747474747474,
86
+ "2009 Falĺ": 46.7005076142132,
87
+ "2010 Falĺ": 40.4040404040404,
88
+ "2012 Spring": 43.5,
89
+ "2009 Spring": 43.21608040201005,
90
+ "2012 Falĺ": 45.40816326530612,
91
+ "2022 Spring": 41.83673469387755,
92
+ "2014 Spring": 42.05128205128205,
93
+ "2022 Fall": 43.36734693877551,
94
+ "2014 Fall": 52.604166666666664,
95
+ "2024 Spring": 51.26903553299492,
96
+ "2015 Spring": 44.94949494949495,
97
+ "2023 Spring": 47.93814432989691,
98
+ "2021 Fall": 44.329896907216494,
99
+ "2015 Fall": 42.63157894736842,
100
+ "2023 Fall": 42.2680412371134,
101
+ "2021 Spring": 44.0,
102
+ "2013 Spring": 48.95833333333333,
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 Falĺ": 77.15736040609137,
137
+ "2011 Falĺ": 72.72727272727273,
138
+ "2009 Falĺ": 71.06598984771574,
139
+ "2010 Falĺ": 75.75757575757575,
140
+ "2012 Spring": 75.0,
141
+ "2009 Spring": 72.8643216080402,
142
+ "2012 Falĺ": 78.57142857142857,
143
+ "2022 Spring": 70.40816326530613,
144
+ "2014 Spring": 72.82051282051282,
145
+ "2022 Fall": 76.53061224489795,
146
+ "2014 Fall": 76.5625,
147
+ "2024 Spring": 82.23350253807106,
148
+ "2015 Spring": 73.23232323232324,
149
+ "2023 Spring": 75.25773195876289,
150
+ "2021 Fall": 72.16494845360825,
151
+ "2015 Fall": 75.78947368421053,
152
+ "2023 Fall": 78.35051546391753,
153
+ "2021 Spring": 80.5,
154
+ "2013 Spring": 74.47916666666666,
155
+ "2013 Fall": 78.01047120418848,
156
+ "overall_accuracy": 75.44063079777365
157
  },
158
  {
159
+ "model_name": "model-meta-llama-Llama-3.2-1B-Instruct",
160
+ "2011 Spring": 18.181818181818183,
161
+ "2010 Spring": 25.5,
162
+ "2008 Falĺ": 20.304568527918782,
163
+ "2011 Falĺ": 30.303030303030305,
164
+ "2009 Falĺ": 25.380710659898476,
165
+ "2010 Falĺ": 23.737373737373737,
166
+ "2012 Spring": 29.5,
167
+ "2009 Spring": 29.145728643216078,
168
+ "2012 Falĺ": 26.53061224489796,
169
+ "2022 Spring": 20.918367346938776,
170
+ "2014 Spring": 25.64102564102564,
171
+ "2022 Fall": 23.46938775510204,
172
+ "2014 Fall": 26.041666666666668,
173
+ "2024 Spring": 25.380710659898476,
174
+ "2015 Spring": 26.767676767676768,
175
+ "2023 Spring": 22.68041237113402,
176
+ "2021 Fall": 23.195876288659793,
177
+ "2015 Fall": 23.684210526315788,
178
+ "2023 Fall": 27.835051546391753,
179
+ "2021 Spring": 26.5,
180
+ "2013 Spring": 21.875,
181
+ "2013 Fall": 23.036649214659686,
182
+ "overall_accuracy": 24.81447124304267
183
  },
184
  {
185
  "model_name": "model-speakleash-Bielik-11B-v2.2-Instruct",
186
+ "2011 Spring": 59.59595959595959,
187
+ "2010 Spring": 62.0,
188
+ "2008 Falĺ": 59.89847715736041,
189
+ "2011 Falĺ": 60.1010101010101,
190
+ "2009 Falĺ": 58.37563451776649,
191
+ "2010 Falĺ": 63.13131313131313,
192
+ "2012 Spring": 61.0,
193
+ "2009 Spring": 63.31658291457286,
194
+ "2012 Falĺ": 63.26530612244898,
195
+ "2022 Spring": 58.16326530612245,
196
+ "2014 Spring": 57.948717948717956,
197
+ "2022 Fall": 67.85714285714286,
198
+ "2014 Fall": 63.541666666666664,
199
+ "2024 Spring": 65.48223350253807,
200
+ "2015 Spring": 59.59595959595959,
201
+ "2023 Spring": 63.4020618556701,
202
+ "2021 Fall": 62.371134020618555,
203
+ "2015 Fall": 61.578947368421055,
204
+ "2023 Fall": 62.88659793814433,
205
+ "2021 Spring": 64.5,
206
+ "2013 Spring": 61.458333333333336,
207
+ "2013 Fall": 61.78010471204188,
208
  "overall_accuracy": 61.87384044526901
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 Falĺ": 36.04060913705584,
241
+ "2011 Falĺ": 58.58585858585859,
242
+ "2009 Falĺ": 54.314720812182735,
243
+ "2010 Falĺ": 54.04040404040404,
244
+ "2012 Spring": 61.0,
245
+ "2009 Spring": 54.2713567839196,
246
+ "2012 Falĺ": 58.16326530612245,
247
+ "2022 Spring": 60.204081632653065,
248
+ "2014 Spring": 57.43589743589743,
249
+ "2022 Fall": 57.6530612244898,
250
+ "2014 Fall": 63.541666666666664,
251
+ "2024 Spring": 68.02030456852792,
252
+ "2015 Spring": 62.121212121212125,
253
+ "2023 Spring": 62.371134020618555,
254
+ "2021 Fall": 61.34020618556701,
255
+ "2015 Fall": 57.89473684210527,
256
+ "2023 Fall": 62.371134020618555,
257
+ "2021 Spring": 65.0,
258
+ "2013 Spring": 57.8125,
259
+ "2013 Fall": 61.25654450261781,
260
+ "overall_accuracy": 55.14842300556586
261
  },
262
  {
263
  "model_name": "model-Qwen-Qwen2.5-7B-Instruct",
264
+ "2011 Spring": 50.0,
265
+ "2010 Spring": 52.5,
266
+ "2008 Falĺ": 54.314720812182735,
267
+ "2011 Falĺ": 59.59595959595959,
268
+ "2009 Falĺ": 45.68527918781726,
269
+ "2010 Falĺ": 48.484848484848484,
270
+ "2012 Spring": 45.0,
271
+ "2009 Spring": 51.75879396984925,
272
+ "2012 Falĺ": 48.97959183673469,
273
+ "2022 Spring": 50.0,
274
+ "2014 Spring": 48.717948717948715,
275
+ "2022 Fall": 52.55102040816326,
276
+ "2014 Fall": 53.645833333333336,
277
+ "2024 Spring": 55.32994923857868,
278
+ "2015 Spring": 47.474747474747474,
279
+ "2023 Spring": 51.546391752577314,
280
+ "2021 Fall": 58.24742268041238,
281
+ "2015 Fall": 50.0,
282
+ "2023 Fall": 50.0,
283
+ "2021 Spring": 50.5,
284
+ "2013 Spring": 56.770833333333336,
285
+ "2013 Fall": 50.26178010471204,
286
  "overall_accuracy": 51.41465677179963
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 Falĺ": 79.69543147208121,
293
+ "2011 Falĺ": 83.33333333333334,
294
+ "2009 Falĺ": 81.21827411167513,
295
+ "2010 Falĺ": 80.8080808080808,
296
+ "2012 Spring": 80.0,
297
+ "2009 Spring": 72.8643216080402,
298
+ "2012 Falĺ": 81.12244897959184,
299
+ "2022 Spring": 79.59183673469387,
300
+ "2014 Spring": 76.41025641025641,
301
+ "2022 Fall": 82.14285714285714,
302
+ "2014 Fall": 87.5,
303
+ "2024 Spring": 86.29441624365482,
304
+ "2015 Spring": 77.77777777777779,
305
+ "2023 Spring": 78.8659793814433,
306
+ "2021 Fall": 81.44329896907216,
307
+ "2015 Fall": 78.42105263157895,
308
+ "2023 Fall": 83.50515463917526,
309
+ "2021 Spring": 84.5,
310
+ "2013 Spring": 77.60416666666666,
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 Falĺ": 38.07106598984771,
371
+ "2011 Falĺ": 40.4040404040404,
372
+ "2009 Falĺ": 36.04060913705584,
373
+ "2010 Falĺ": 38.38383838383838,
374
+ "2012 Spring": 40.5,
375
+ "2009 Spring": 35.678391959798994,
376
+ "2012 Falĺ": 46.42857142857143,
377
+ "2022 Spring": 39.285714285714285,
378
+ "2014 Spring": 37.94871794871795,
379
+ "2022 Fall": 41.83673469387755,
380
+ "2014 Fall": 43.75,
381
+ "2024 Spring": 44.67005076142132,
382
+ "2015 Spring": 38.38383838383838,
383
+ "2023 Spring": 41.23711340206185,
384
+ "2021 Fall": 45.36082474226804,
385
+ "2015 Fall": 32.631578947368425,
386
+ "2023 Fall": 44.84536082474227,
387
+ "2021 Spring": 40.5,
388
+ "2013 Spring": 41.14583333333333,
389
+ "2013 Fall": 40.31413612565445,
390
+ "overall_accuracy": 40.60760667903525
391
+ },
392
+ {
393
+ "model_name": "model-mistralai-Mistral-Small-Instruct-2409",
394
+ "2011 Spring": 46.464646464646464,
395
+ "2010 Spring": 54.0,
396
+ "2008 Falĺ": 51.26903553299492,
397
+ "2011 Falĺ": 52.02020202020202,
398
+ "2009 Falĺ": 45.68527918781726,
399
+ "2010 Falĺ": 50.0,
400
+ "2012 Spring": 56.49999999999999,
401
+ "2009 Spring": 52.26130653266332,
402
+ "2012 Falĺ": 49.48979591836735,
403
+ "2022 Spring": 48.97959183673469,
404
+ "2014 Spring": 48.205128205128204,
405
+ "2022 Fall": 52.04081632653062,
406
+ "2014 Fall": 48.95833333333333,
407
+ "2024 Spring": 58.37563451776649,
408
+ "2015 Spring": 52.02020202020202,
409
+ "2023 Spring": 53.09278350515464,
410
+ "2021 Fall": 53.608247422680414,
411
+ "2015 Fall": 47.89473684210526,
412
+ "2023 Fall": 52.0618556701031,
413
+ "2021 Spring": 55.00000000000001,
414
+ "2013 Spring": 49.47916666666667,
415
+ "2013 Fall": 52.35602094240838,
416
+ "overall_accuracy": 51.36827458256029
417
+ },
418
+ {
419
+ "model_name": "model-OpenMeditron-Meditron3-70B",
420
+ "2011 Spring": 64.14141414141415,
421
+ "2010 Spring": 73.5,
422
+ "2008 Falĺ": 62.43654822335025,
423
+ "2011 Falĺ": 69.1919191919192,
424
+ "2009 Falĺ": 58.88324873096447,
425
+ "2010 Falĺ": 61.111111111111114,
426
+ "2012 Spring": 68.5,
427
+ "2009 Spring": 59.2964824120603,
428
+ "2012 Falĺ": 66.83673469387756,
429
+ "2022 Spring": 70.91836734693877,
430
+ "2014 Spring": 70.25641025641025,
431
+ "2022 Fall": 63.775510204081634,
432
+ "2014 Fall": 69.27083333333334,
433
+ "2024 Spring": 77.66497461928934,
434
+ "2015 Spring": 67.67676767676768,
435
+ "2023 Spring": 67.0103092783505,
436
+ "2021 Fall": 64.43298969072166,
437
+ "2015 Fall": 66.3157894736842,
438
+ "2023 Fall": 68.55670103092784,
439
+ "2021 Spring": 70.5,
440
+ "2013 Spring": 65.625,
441
+ "2013 Fall": 66.49214659685863,
442
+ "overall_accuracy": 66.92949907235621
443
  }
444
  ]