Spaces:
Sleeping
Sleeping
Update ShoppingMMLU_overall.json
Browse files- ShoppingMMLU_overall.json +737 -104
ShoppingMMLU_overall.json
CHANGED
@@ -190,244 +190,877 @@
|
|
190 |
"Overall": 67.76
|
191 |
}
|
192 |
},
|
193 |
-
"
|
194 |
"META": {
|
195 |
"Method": [
|
196 |
-
"
|
197 |
-
"https://huggingface.co/meta-llama/Meta-Llama-3-70B"
|
198 |
],
|
199 |
-
"Parameters": "
|
200 |
-
"Org": "
|
201 |
-
"OpenSource": "
|
202 |
"Verified": "Yes"
|
203 |
},
|
204 |
-
|
205 |
-
"Overall":
|
206 |
},
|
207 |
-
"
|
208 |
-
"Overall": 63
|
209 |
},
|
210 |
-
"
|
211 |
-
"Overall":
|
212 |
},
|
213 |
-
"
|
214 |
-
"Overall":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
215 |
}
|
216 |
},
|
217 |
-
"
|
218 |
"META": {
|
219 |
"Method": [
|
220 |
-
"
|
221 |
-
"https://huggingface.co/
|
222 |
],
|
223 |
-
"Parameters": "
|
224 |
-
"Org": "
|
225 |
"OpenSource": "Yes",
|
226 |
"Verified": "Yes"
|
227 |
},
|
228 |
"Shopping Concept Understanding": {
|
229 |
-
"Overall":
|
230 |
},
|
231 |
"Shopping Knowledge Reasoning": {
|
232 |
-
"Overall":
|
233 |
},
|
234 |
"User Behavior Alignment": {
|
235 |
-
"Overall":
|
236 |
},
|
237 |
"Multi-lingual Abilities": {
|
238 |
-
"Overall":
|
239 |
}
|
240 |
},
|
241 |
-
"
|
242 |
"META": {
|
243 |
"Method": [
|
244 |
-
"
|
245 |
-
"https://huggingface.co/
|
246 |
],
|
247 |
-
"Parameters": "
|
248 |
-
"Org": "
|
249 |
"OpenSource": "Yes",
|
250 |
"Verified": "Yes"
|
251 |
},
|
252 |
"Shopping Concept Understanding": {
|
253 |
-
"Overall":
|
254 |
},
|
255 |
"Shopping Knowledge Reasoning": {
|
256 |
-
"Overall":
|
257 |
},
|
258 |
"User Behavior Alignment": {
|
259 |
-
"Overall":
|
260 |
},
|
261 |
"Multi-lingual Abilities": {
|
262 |
-
"Overall":
|
263 |
}
|
264 |
},
|
265 |
-
"
|
266 |
"META": {
|
267 |
"Method": [
|
268 |
-
"
|
269 |
-
"https://huggingface.co/
|
270 |
],
|
271 |
-
"Parameters": "
|
272 |
-
"Org": "
|
273 |
"OpenSource": "Yes",
|
274 |
"Verified": "Yes"
|
275 |
},
|
276 |
"Shopping Concept Understanding": {
|
277 |
-
"Overall":
|
278 |
},
|
279 |
"Shopping Knowledge Reasoning": {
|
280 |
-
"Overall":
|
281 |
},
|
282 |
"User Behavior Alignment": {
|
283 |
-
"Overall":
|
284 |
},
|
285 |
"Multi-lingual Abilities": {
|
286 |
-
"Overall":
|
287 |
}
|
288 |
},
|
289 |
-
"
|
290 |
"META": {
|
291 |
"Method": [
|
292 |
-
"
|
293 |
-
"https://huggingface.co/
|
294 |
],
|
295 |
"Parameters": "13B",
|
296 |
-
"Org": "
|
297 |
"OpenSource": "Yes",
|
298 |
"Verified": "Yes"
|
299 |
},
|
300 |
"Shopping Concept Understanding": {
|
301 |
-
"Overall":
|
302 |
},
|
303 |
"Shopping Knowledge Reasoning": {
|
304 |
-
"Overall":
|
305 |
},
|
306 |
"User Behavior Alignment": {
|
307 |
-
"Overall":
|
308 |
},
|
309 |
"Multi-lingual Abilities": {
|
310 |
-
"Overall":
|
311 |
}
|
312 |
},
|
313 |
-
"
|
314 |
"META": {
|
315 |
"Method": [
|
316 |
-
"
|
317 |
-
"https://huggingface.co/
|
318 |
],
|
319 |
-
"Parameters": "
|
320 |
-
"Org": "
|
321 |
"OpenSource": "Yes",
|
322 |
"Verified": "Yes"
|
323 |
},
|
324 |
"Shopping Concept Understanding": {
|
325 |
-
"Overall":
|
326 |
},
|
327 |
"Shopping Knowledge Reasoning": {
|
328 |
-
"Overall":
|
329 |
},
|
330 |
"User Behavior Alignment": {
|
331 |
-
"Overall":
|
332 |
},
|
333 |
"Multi-lingual Abilities": {
|
334 |
-
"Overall":
|
335 |
}
|
336 |
},
|
337 |
-
"
|
338 |
"META": {
|
339 |
"Method": [
|
340 |
-
"
|
341 |
-
"https://huggingface.co/
|
342 |
],
|
343 |
-
"Parameters": "
|
344 |
-
"Org": "
|
345 |
"OpenSource": "Yes",
|
346 |
"Verified": "Yes"
|
347 |
},
|
348 |
"Shopping Concept Understanding": {
|
349 |
-
"Overall":
|
350 |
},
|
351 |
"Shopping Knowledge Reasoning": {
|
352 |
-
"Overall":
|
353 |
},
|
354 |
"User Behavior Alignment": {
|
355 |
-
"Overall":
|
356 |
},
|
357 |
"Multi-lingual Abilities": {
|
358 |
-
"Overall":
|
359 |
}
|
360 |
},
|
361 |
-
"
|
362 |
"META": {
|
363 |
"Method": [
|
364 |
-
"
|
365 |
-
"https://huggingface.co/
|
366 |
],
|
367 |
-
"Parameters": "
|
368 |
-
"Org": "
|
369 |
"OpenSource": "Yes",
|
370 |
"Verified": "Yes"
|
371 |
},
|
372 |
"Shopping Concept Understanding": {
|
373 |
-
"Overall":
|
374 |
},
|
375 |
"Shopping Knowledge Reasoning": {
|
376 |
-
"Overall":
|
377 |
},
|
378 |
"User Behavior Alignment": {
|
379 |
-
"Overall":
|
380 |
},
|
381 |
"Multi-lingual Abilities": {
|
382 |
-
"Overall":
|
383 |
}
|
384 |
},
|
385 |
-
"
|
386 |
"META": {
|
387 |
"Method": [
|
388 |
-
"
|
389 |
-
"https://huggingface.co/meta-llama/Llama-2-7b-chat-hf"
|
390 |
],
|
391 |
-
"Parameters": "
|
392 |
-
"Org": "
|
393 |
-
"OpenSource": "
|
394 |
"Verified": "Yes"
|
395 |
},
|
396 |
-
|
397 |
-
"Overall":
|
398 |
},
|
399 |
-
"
|
400 |
-
"Overall":
|
401 |
},
|
402 |
-
"
|
403 |
-
"Overall":
|
404 |
},
|
405 |
-
"
|
406 |
-
"Overall":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
407 |
}
|
408 |
},
|
409 |
-
"
|
410 |
"META": {
|
411 |
"Method": [
|
412 |
-
"
|
413 |
-
"https://huggingface.co/meta-llama/Llama-2-7b-hf"
|
414 |
],
|
415 |
-
"Parameters": "
|
416 |
-
"Org": "
|
417 |
-
"OpenSource": "
|
418 |
"Verified": "Yes"
|
419 |
},
|
420 |
-
|
421 |
-
"Overall":
|
422 |
},
|
423 |
-
"
|
424 |
-
"Overall":
|
425 |
},
|
426 |
-
"
|
427 |
-
"Overall":
|
428 |
},
|
429 |
-
"
|
430 |
-
"Overall":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
431 |
}
|
432 |
},
|
433 |
}
|
|
|
190 |
"Overall": 67.76
|
191 |
}
|
192 |
},
|
193 |
+
"Alpaca": {
|
194 |
"META": {
|
195 |
"Method": [
|
196 |
+
"Alpaca",
|
|
|
197 |
],
|
198 |
+
"Parameters": "7B",
|
199 |
+
"Org": "OpenAI",
|
200 |
+
"OpenSource": "No",
|
201 |
"Verified": "Yes"
|
202 |
},
|
203 |
+
"MedQA": {
|
204 |
+
"Overall": 80.75
|
205 |
},
|
206 |
+
"MedMCQA": {
|
207 |
+
"Overall": 71.63
|
208 |
},
|
209 |
+
"MMLU-Medicine": {
|
210 |
+
"Overall": 70.17
|
211 |
},
|
212 |
+
"PubMedQA": {
|
213 |
+
"Overall": 67.76
|
214 |
+
},
|
215 |
+
"Referral QA": {
|
216 |
+
"Overall": 67.76
|
217 |
+
},
|
218 |
+
"Treat Recom.": {
|
219 |
+
"Overall": 67.76
|
220 |
+
},
|
221 |
+
"MIMIC": {
|
222 |
+
"Overall": 67.76
|
223 |
+
},
|
224 |
+
"IU-Xray": {
|
225 |
+
"Overall": 67.76
|
226 |
+
},
|
227 |
+
"Hospitaliz. Summari.": {
|
228 |
+
"Overall": 67.76
|
229 |
+
},
|
230 |
+
"Patient Education": {
|
231 |
+
"Overall": 67.76
|
232 |
+
},
|
233 |
+
"BC5": {
|
234 |
+
"Overall": 67.76
|
235 |
+
},
|
236 |
+
"NCBI": {
|
237 |
+
"Overall": 67.76
|
238 |
+
},
|
239 |
+
"DDI": {
|
240 |
+
"Overall": 67.76
|
241 |
+
},
|
242 |
+
"GAD": {
|
243 |
+
"Overall": 67.76
|
244 |
+
},
|
245 |
+
"HoC": {
|
246 |
+
"Overall": 67.76
|
247 |
+
},
|
248 |
+
"Pharma. QA": {
|
249 |
+
"Overall": 67.76
|
250 |
+
},
|
251 |
+
"Drug Inter.": {
|
252 |
+
"Overall": 67.76
|
253 |
}
|
254 |
},
|
255 |
+
"Vicuna-7B-v1.5": {
|
256 |
"META": {
|
257 |
"Method": [
|
258 |
+
"Vicuna-7B-v1.5",
|
259 |
+
"https://huggingface.co/lmsys/vicuna-7b-v1.5"
|
260 |
],
|
261 |
+
"Parameters": "7B",
|
262 |
+
"Org": "LMSys",
|
263 |
"OpenSource": "Yes",
|
264 |
"Verified": "Yes"
|
265 |
},
|
266 |
"Shopping Concept Understanding": {
|
267 |
+
"Overall": 53.46
|
268 |
},
|
269 |
"Shopping Knowledge Reasoning": {
|
270 |
+
"Overall": 45.06
|
271 |
},
|
272 |
"User Behavior Alignment": {
|
273 |
+
"Overall": 41.11
|
274 |
},
|
275 |
"Multi-lingual Abilities": {
|
276 |
+
"Overall": 43.82
|
277 |
}
|
278 |
},
|
279 |
+
"LLaMA2-7B-Chat": {
|
280 |
"META": {
|
281 |
"Method": [
|
282 |
+
"LLaMA2-7B-Chat",
|
283 |
+
"https://huggingface.co/meta-llama/Llama-2-7b-chat-hf"
|
284 |
],
|
285 |
+
"Parameters": "7B",
|
286 |
+
"Org": "Meta",
|
287 |
"OpenSource": "Yes",
|
288 |
"Verified": "Yes"
|
289 |
},
|
290 |
"Shopping Concept Understanding": {
|
291 |
+
"Overall": 51.67
|
292 |
},
|
293 |
"Shopping Knowledge Reasoning": {
|
294 |
+
"Overall": 43.48
|
295 |
},
|
296 |
"User Behavior Alignment": {
|
297 |
+
"Overall": 41.42
|
298 |
},
|
299 |
"Multi-lingual Abilities": {
|
300 |
+
"Overall": 40.43
|
301 |
}
|
302 |
},
|
303 |
+
"Mistral-7B-Instruct": {
|
304 |
"META": {
|
305 |
"Method": [
|
306 |
+
"Mistral-7B-Instruct",
|
307 |
+
"https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2"
|
308 |
],
|
309 |
+
"Parameters": "7B",
|
310 |
+
"Org": "MistralAI",
|
311 |
"OpenSource": "Yes",
|
312 |
"Verified": "Yes"
|
313 |
},
|
314 |
"Shopping Concept Understanding": {
|
315 |
+
"Overall": 62.03
|
316 |
},
|
317 |
"Shopping Knowledge Reasoning": {
|
318 |
+
"Overall": 46.36
|
319 |
},
|
320 |
"User Behavior Alignment": {
|
321 |
+
"Overall": 42.21
|
322 |
},
|
323 |
"Multi-lingual Abilities": {
|
324 |
+
"Overall": 43.32
|
325 |
}
|
326 |
},
|
327 |
+
"Vicuna-13B-v1.5": {
|
328 |
"META": {
|
329 |
"Method": [
|
330 |
+
"Vicuna-13B-v1.5",
|
331 |
+
"https://huggingface.co/lmsys/vicuna-13b-v1.5"
|
332 |
],
|
333 |
"Parameters": "13B",
|
334 |
+
"Org": "LMSys",
|
335 |
"OpenSource": "Yes",
|
336 |
"Verified": "Yes"
|
337 |
},
|
338 |
"Shopping Concept Understanding": {
|
339 |
+
"Overall": 59.64
|
340 |
},
|
341 |
"Shopping Knowledge Reasoning": {
|
342 |
+
"Overall": 52.63
|
343 |
},
|
344 |
"User Behavior Alignment": {
|
345 |
+
"Overall": 49.81
|
346 |
},
|
347 |
"Multi-lingual Abilities": {
|
348 |
+
"Overall": 49.64
|
349 |
}
|
350 |
},
|
351 |
+
"LLaMA-2-13B-Chat": {
|
352 |
"META": {
|
353 |
"Method": [
|
354 |
+
"LLaMA-2-13B-Chat",
|
355 |
+
"https://huggingface.co/meta-llama/Llama-2-13b-chat-hf"
|
356 |
],
|
357 |
+
"Parameters": "13B",
|
358 |
+
"Org": "Meta",
|
359 |
"OpenSource": "Yes",
|
360 |
"Verified": "Yes"
|
361 |
},
|
362 |
"Shopping Concept Understanding": {
|
363 |
+
"Overall": 51.79
|
364 |
},
|
365 |
"Shopping Knowledge Reasoning": {
|
366 |
+
"Overall": 45.01
|
367 |
},
|
368 |
"User Behavior Alignment": {
|
369 |
+
"Overall": 39.95
|
370 |
},
|
371 |
"Multi-lingual Abilities": {
|
372 |
+
"Overall": 42.99
|
373 |
}
|
374 |
},
|
375 |
+
"LLaMA-2-70B": {
|
376 |
"META": {
|
377 |
"Method": [
|
378 |
+
"LLaMA-2-70B",
|
379 |
+
"https://huggingface.co/meta-llama/Llama-2-70b-chat-hf"
|
380 |
],
|
381 |
+
"Parameters": "70B",
|
382 |
+
"Org": "Meta",
|
383 |
"OpenSource": "Yes",
|
384 |
"Verified": "Yes"
|
385 |
},
|
386 |
"Shopping Concept Understanding": {
|
387 |
+
"Overall": 61.84
|
388 |
},
|
389 |
"Shopping Knowledge Reasoning": {
|
390 |
+
"Overall": 40.73
|
391 |
},
|
392 |
"User Behavior Alignment": {
|
393 |
+
"Overall": 44.2
|
394 |
},
|
395 |
"Multi-lingual Abilities": {
|
396 |
+
"Overall": 47.04
|
397 |
}
|
398 |
},
|
399 |
+
"LLaMA-3-70B": {
|
400 |
"META": {
|
401 |
"Method": [
|
402 |
+
"LLaMA-3-70B",
|
403 |
+
"https://huggingface.co/meta-llama/Meta-Llama-3-70B"
|
404 |
],
|
405 |
+
"Parameters": "70B",
|
406 |
+
"Org": "Meta",
|
407 |
"OpenSource": "Yes",
|
408 |
"Verified": "Yes"
|
409 |
},
|
410 |
"Shopping Concept Understanding": {
|
411 |
+
"Overall": 69.59
|
412 |
},
|
413 |
"Shopping Knowledge Reasoning": {
|
414 |
+
"Overall": 63.56
|
415 |
},
|
416 |
"User Behavior Alignment": {
|
417 |
+
"Overall": 55.77
|
418 |
},
|
419 |
"Multi-lingual Abilities": {
|
420 |
+
"Overall": 58.95
|
421 |
}
|
422 |
},
|
423 |
+
"Huatuo": {
|
424 |
"META": {
|
425 |
"Method": [
|
426 |
+
"Huatuo"
|
|
|
427 |
],
|
428 |
+
"Parameters": "",
|
429 |
+
"Org": "OpenAI",
|
430 |
+
"OpenSource": "No",
|
431 |
"Verified": "Yes"
|
432 |
},
|
433 |
+
"MedQA": {
|
434 |
+
"Overall": 80.75
|
435 |
},
|
436 |
+
"MedMCQA": {
|
437 |
+
"Overall": 71.63
|
438 |
},
|
439 |
+
"MMLU-Medicine": {
|
440 |
+
"Overall": 70.17
|
441 |
},
|
442 |
+
"PubMedQA": {
|
443 |
+
"Overall": 67.76
|
444 |
+
},
|
445 |
+
"Referral QA": {
|
446 |
+
"Overall": 67.76
|
447 |
+
},
|
448 |
+
"Treat Recom.": {
|
449 |
+
"Overall": 67.76
|
450 |
+
},
|
451 |
+
"MIMIC": {
|
452 |
+
"Overall": 67.76
|
453 |
+
},
|
454 |
+
"IU-Xray": {
|
455 |
+
"Overall": 67.76
|
456 |
+
},
|
457 |
+
"Hospitaliz. Summari.": {
|
458 |
+
"Overall": 67.76
|
459 |
+
},
|
460 |
+
"Patient Education": {
|
461 |
+
"Overall": 67.76
|
462 |
+
},
|
463 |
+
"BC5": {
|
464 |
+
"Overall": 67.76
|
465 |
+
},
|
466 |
+
"NCBI": {
|
467 |
+
"Overall": 67.76
|
468 |
+
},
|
469 |
+
"DDI": {
|
470 |
+
"Overall": 67.76
|
471 |
+
},
|
472 |
+
"GAD": {
|
473 |
+
"Overall": 67.76
|
474 |
+
},
|
475 |
+
"HoC": {
|
476 |
+
"Overall": 67.76
|
477 |
+
},
|
478 |
+
"Pharma. QA": {
|
479 |
+
"Overall": 67.76
|
480 |
+
},
|
481 |
+
"Drug Inter.": {
|
482 |
+
"Overall": 67.76
|
483 |
}
|
484 |
},
|
485 |
+
"ChatDoctor": {
|
486 |
"META": {
|
487 |
"Method": [
|
488 |
+
"ChatDoctor"
|
|
|
489 |
],
|
490 |
+
"Parameters": "",
|
491 |
+
"Org": "OpenAI",
|
492 |
+
"OpenSource": "No",
|
493 |
"Verified": "Yes"
|
494 |
},
|
495 |
+
"MedQA": {
|
496 |
+
"Overall": 80.75
|
497 |
},
|
498 |
+
"MedMCQA": {
|
499 |
+
"Overall": 71.63
|
500 |
},
|
501 |
+
"MMLU-Medicine": {
|
502 |
+
"Overall": 70.17
|
503 |
},
|
504 |
+
"PubMedQA": {
|
505 |
+
"Overall": 67.76
|
506 |
+
},
|
507 |
+
"Referral QA": {
|
508 |
+
"Overall": 67.76
|
509 |
+
},
|
510 |
+
"Treat Recom.": {
|
511 |
+
"Overall": 67.76
|
512 |
+
},
|
513 |
+
"MIMIC": {
|
514 |
+
"Overall": 67.76
|
515 |
+
},
|
516 |
+
"IU-Xray": {
|
517 |
+
"Overall": 67.76
|
518 |
+
},
|
519 |
+
"Hospitaliz. Summari.": {
|
520 |
+
"Overall": 67.76
|
521 |
+
},
|
522 |
+
"Patient Education": {
|
523 |
+
"Overall": 67.76
|
524 |
+
},
|
525 |
+
"BC5": {
|
526 |
+
"Overall": 67.76
|
527 |
+
},
|
528 |
+
"NCBI": {
|
529 |
+
"Overall": 67.76
|
530 |
+
},
|
531 |
+
"DDI": {
|
532 |
+
"Overall": 67.76
|
533 |
+
},
|
534 |
+
"GAD": {
|
535 |
+
"Overall": 67.76
|
536 |
+
},
|
537 |
+
"HoC": {
|
538 |
+
"Overall": 67.76
|
539 |
+
},
|
540 |
+
"Pharma. QA": {
|
541 |
+
"Overall": 67.76
|
542 |
+
},
|
543 |
+
"Drug Inter.": {
|
544 |
+
"Overall": 67.76
|
545 |
+
}
|
546 |
+
},
|
547 |
+
"PMC-LLaMA": {
|
548 |
+
"META": {
|
549 |
+
"Method": [
|
550 |
+
"PMC-LLaMA"
|
551 |
+
],
|
552 |
+
"Parameters": "7B",
|
553 |
+
"Org": "OpenAI",
|
554 |
+
"OpenSource": "No",
|
555 |
+
"Verified": "Yes"
|
556 |
+
},
|
557 |
+
"MedQA": {
|
558 |
+
"Overall": 80.75
|
559 |
+
},
|
560 |
+
"MedMCQA": {
|
561 |
+
"Overall": 71.63
|
562 |
+
},
|
563 |
+
"MMLU-Medicine": {
|
564 |
+
"Overall": 70.17
|
565 |
+
},
|
566 |
+
"PubMedQA": {
|
567 |
+
"Overall": 67.76
|
568 |
+
},
|
569 |
+
"Referral QA": {
|
570 |
+
"Overall": 67.76
|
571 |
+
},
|
572 |
+
"Treat Recom.": {
|
573 |
+
"Overall": 67.76
|
574 |
+
},
|
575 |
+
"MIMIC": {
|
576 |
+
"Overall": 67.76
|
577 |
+
},
|
578 |
+
"IU-Xray": {
|
579 |
+
"Overall": 67.76
|
580 |
+
},
|
581 |
+
"Hospitaliz. Summari.": {
|
582 |
+
"Overall": 67.76
|
583 |
+
},
|
584 |
+
"Patient Education": {
|
585 |
+
"Overall": 67.76
|
586 |
+
},
|
587 |
+
"BC5": {
|
588 |
+
"Overall": 67.76
|
589 |
+
},
|
590 |
+
"NCBI": {
|
591 |
+
"Overall": 67.76
|
592 |
+
},
|
593 |
+
"DDI": {
|
594 |
+
"Overall": 67.76
|
595 |
+
},
|
596 |
+
"GAD": {
|
597 |
+
"Overall": 67.76
|
598 |
+
},
|
599 |
+
"HoC": {
|
600 |
+
"Overall": 67.76
|
601 |
+
},
|
602 |
+
"Pharma. QA": {
|
603 |
+
"Overall": 67.76
|
604 |
+
},
|
605 |
+
"Drug Inter.": {
|
606 |
+
"Overall": 67.76
|
607 |
+
}
|
608 |
+
},
|
609 |
+
"Baize-Healthcare": {
|
610 |
+
"META": {
|
611 |
+
"Method": [
|
612 |
+
"Baize-Healthcare"
|
613 |
+
],
|
614 |
+
"Parameters": "7B",
|
615 |
+
"Org": "OpenAI",
|
616 |
+
"OpenSource": "No",
|
617 |
+
"Verified": "Yes"
|
618 |
+
},
|
619 |
+
"MedQA": {
|
620 |
+
"Overall": 80.75
|
621 |
+
},
|
622 |
+
"MedMCQA": {
|
623 |
+
"Overall": 71.63
|
624 |
+
},
|
625 |
+
"MMLU-Medicine": {
|
626 |
+
"Overall": 70.17
|
627 |
+
},
|
628 |
+
"PubMedQA": {
|
629 |
+
"Overall": 67.76
|
630 |
+
},
|
631 |
+
"Referral QA": {
|
632 |
+
"Overall": 67.76
|
633 |
+
},
|
634 |
+
"Treat Recom.": {
|
635 |
+
"Overall": 67.76
|
636 |
+
},
|
637 |
+
"MIMIC": {
|
638 |
+
"Overall": 67.76
|
639 |
+
},
|
640 |
+
"IU-Xray": {
|
641 |
+
"Overall": 67.76
|
642 |
+
},
|
643 |
+
"Hospitaliz. Summari.": {
|
644 |
+
"Overall": 67.76
|
645 |
+
},
|
646 |
+
"Patient Education": {
|
647 |
+
"Overall": 67.76
|
648 |
+
},
|
649 |
+
"BC5": {
|
650 |
+
"Overall": 67.76
|
651 |
+
},
|
652 |
+
"NCBI": {
|
653 |
+
"Overall": 67.76
|
654 |
+
},
|
655 |
+
"DDI": {
|
656 |
+
"Overall": 67.76
|
657 |
+
},
|
658 |
+
"GAD": {
|
659 |
+
"Overall": 67.76
|
660 |
+
},
|
661 |
+
"HoC": {
|
662 |
+
"Overall": 67.76
|
663 |
+
},
|
664 |
+
"Pharma. QA": {
|
665 |
+
"Overall": 67.76
|
666 |
+
},
|
667 |
+
"Drug Inter.": {
|
668 |
+
"Overall": 67.76
|
669 |
+
}
|
670 |
+
},
|
671 |
+
"MedAlpaca": {
|
672 |
+
"META": {
|
673 |
+
"Method": [
|
674 |
+
"MedAlpaca"
|
675 |
+
],
|
676 |
+
"Parameters": "7B",
|
677 |
+
"Org": "OpenAI",
|
678 |
+
"OpenSource": "No",
|
679 |
+
"Verified": "Yes"
|
680 |
+
},
|
681 |
+
"MedQA": {
|
682 |
+
"Overall": 80.75
|
683 |
+
},
|
684 |
+
"MedMCQA": {
|
685 |
+
"Overall": 71.63
|
686 |
+
},
|
687 |
+
"MMLU-Medicine": {
|
688 |
+
"Overall": 70.17
|
689 |
+
},
|
690 |
+
"PubMedQA": {
|
691 |
+
"Overall": 67.76
|
692 |
+
},
|
693 |
+
"Referral QA": {
|
694 |
+
"Overall": 67.76
|
695 |
+
},
|
696 |
+
"Treat Recom.": {
|
697 |
+
"Overall": 67.76
|
698 |
+
},
|
699 |
+
"MIMIC": {
|
700 |
+
"Overall": 67.76
|
701 |
+
},
|
702 |
+
"IU-Xray": {
|
703 |
+
"Overall": 67.76
|
704 |
+
},
|
705 |
+
"Hospitaliz. Summari.": {
|
706 |
+
"Overall": 67.76
|
707 |
+
},
|
708 |
+
"Patient Education": {
|
709 |
+
"Overall": 67.76
|
710 |
+
},
|
711 |
+
"BC5": {
|
712 |
+
"Overall": 67.76
|
713 |
+
},
|
714 |
+
"NCBI": {
|
715 |
+
"Overall": 67.76
|
716 |
+
},
|
717 |
+
"DDI": {
|
718 |
+
"Overall": 67.76
|
719 |
+
},
|
720 |
+
"GAD": {
|
721 |
+
"Overall": 67.76
|
722 |
+
},
|
723 |
+
"HoC": {
|
724 |
+
"Overall": 67.76
|
725 |
+
},
|
726 |
+
"Pharma. QA": {
|
727 |
+
"Overall": 67.76
|
728 |
+
},
|
729 |
+
"Drug Inter.": {
|
730 |
+
"Overall": 67.76
|
731 |
+
}
|
732 |
+
},
|
733 |
+
"Meditron": {
|
734 |
+
"META": {
|
735 |
+
"Method": [
|
736 |
+
"Meditron"
|
737 |
+
],
|
738 |
+
"Parameters": "",
|
739 |
+
"Org": "OpenAI",
|
740 |
+
"OpenSource": "No",
|
741 |
+
"Verified": "Yes"
|
742 |
+
},
|
743 |
+
"MedQA": {
|
744 |
+
"Overall": 80.75
|
745 |
+
},
|
746 |
+
"MedMCQA": {
|
747 |
+
"Overall": 71.63
|
748 |
+
},
|
749 |
+
"MMLU-Medicine": {
|
750 |
+
"Overall": 70.17
|
751 |
+
},
|
752 |
+
"PubMedQA": {
|
753 |
+
"Overall": 67.76
|
754 |
+
},
|
755 |
+
"Referral QA": {
|
756 |
+
"Overall": 67.76
|
757 |
+
},
|
758 |
+
"Treat Recom.": {
|
759 |
+
"Overall": 67.76
|
760 |
+
},
|
761 |
+
"MIMIC": {
|
762 |
+
"Overall": 67.76
|
763 |
+
},
|
764 |
+
"IU-Xray": {
|
765 |
+
"Overall": 67.76
|
766 |
+
},
|
767 |
+
"Hospitaliz. Summari.": {
|
768 |
+
"Overall": 67.76
|
769 |
+
},
|
770 |
+
"Patient Education": {
|
771 |
+
"Overall": 67.76
|
772 |
+
},
|
773 |
+
"BC5": {
|
774 |
+
"Overall": 67.76
|
775 |
+
},
|
776 |
+
"NCBI": {
|
777 |
+
"Overall": 67.76
|
778 |
+
},
|
779 |
+
"DDI": {
|
780 |
+
"Overall": 67.76
|
781 |
+
},
|
782 |
+
"GAD": {
|
783 |
+
"Overall": 67.76
|
784 |
+
},
|
785 |
+
"HoC": {
|
786 |
+
"Overall": 67.76
|
787 |
+
},
|
788 |
+
"Pharma. QA": {
|
789 |
+
"Overall": 67.76
|
790 |
+
},
|
791 |
+
"Drug Inter.": {
|
792 |
+
"Overall": 67.76
|
793 |
+
}
|
794 |
+
},
|
795 |
+
"BioMistral": {
|
796 |
+
"META": {
|
797 |
+
"Method": [
|
798 |
+
"BioMistral"
|
799 |
+
],
|
800 |
+
"Parameters": "",
|
801 |
+
"Org": "OpenAI",
|
802 |
+
"OpenSource": "No",
|
803 |
+
"Verified": "Yes"
|
804 |
+
},
|
805 |
+
"MedQA": {
|
806 |
+
"Overall": 80.75
|
807 |
+
},
|
808 |
+
"MedMCQA": {
|
809 |
+
"Overall": 71.63
|
810 |
+
},
|
811 |
+
"MMLU-Medicine": {
|
812 |
+
"Overall": 70.17
|
813 |
+
},
|
814 |
+
"PubMedQA": {
|
815 |
+
"Overall": 67.76
|
816 |
+
},
|
817 |
+
"Referral QA": {
|
818 |
+
"Overall": 67.76
|
819 |
+
},
|
820 |
+
"Treat Recom.": {
|
821 |
+
"Overall": 67.76
|
822 |
+
},
|
823 |
+
"MIMIC": {
|
824 |
+
"Overall": 67.76
|
825 |
+
},
|
826 |
+
"IU-Xray": {
|
827 |
+
"Overall": 67.76
|
828 |
+
},
|
829 |
+
"Hospitaliz. Summari.": {
|
830 |
+
"Overall": 67.76
|
831 |
+
},
|
832 |
+
"Patient Education": {
|
833 |
+
"Overall": 67.76
|
834 |
+
},
|
835 |
+
"BC5": {
|
836 |
+
"Overall": 67.76
|
837 |
+
},
|
838 |
+
"NCBI": {
|
839 |
+
"Overall": 67.76
|
840 |
+
},
|
841 |
+
"DDI": {
|
842 |
+
"Overall": 67.76
|
843 |
+
},
|
844 |
+
"GAD": {
|
845 |
+
"Overall": 67.76
|
846 |
+
},
|
847 |
+
"HoC": {
|
848 |
+
"Overall": 67.76
|
849 |
+
},
|
850 |
+
"Pharma. QA": {
|
851 |
+
"Overall": 67.76
|
852 |
+
},
|
853 |
+
"Drug Inter.": {
|
854 |
+
"Overall": 67.76
|
855 |
+
}
|
856 |
+
},
|
857 |
+
"PMC-LLaMA": {
|
858 |
+
"META": {
|
859 |
+
"Method": [
|
860 |
+
"PMC-LLaMA"
|
861 |
+
],
|
862 |
+
"Parameters": "",
|
863 |
+
"Org": "OpenAI",
|
864 |
+
"OpenSource": "No",
|
865 |
+
"Verified": "Yes"
|
866 |
+
},
|
867 |
+
"MedQA": {
|
868 |
+
"Overall": 80.75
|
869 |
+
},
|
870 |
+
"MedMCQA": {
|
871 |
+
"Overall": 71.63
|
872 |
+
},
|
873 |
+
"MMLU-Medicine": {
|
874 |
+
"Overall": 70.17
|
875 |
+
},
|
876 |
+
"PubMedQA": {
|
877 |
+
"Overall": 67.76
|
878 |
+
},
|
879 |
+
"Referral QA": {
|
880 |
+
"Overall": 67.76
|
881 |
+
},
|
882 |
+
"Treat Recom.": {
|
883 |
+
"Overall": 67.76
|
884 |
+
},
|
885 |
+
"MIMIC": {
|
886 |
+
"Overall": 67.76
|
887 |
+
},
|
888 |
+
"IU-Xray": {
|
889 |
+
"Overall": 67.76
|
890 |
+
},
|
891 |
+
"Hospitaliz. Summari.": {
|
892 |
+
"Overall": 67.76
|
893 |
+
},
|
894 |
+
"Patient Education": {
|
895 |
+
"Overall": 67.76
|
896 |
+
},
|
897 |
+
"BC5": {
|
898 |
+
"Overall": 67.76
|
899 |
+
},
|
900 |
+
"NCBI": {
|
901 |
+
"Overall": 67.76
|
902 |
+
},
|
903 |
+
"DDI": {
|
904 |
+
"Overall": 67.76
|
905 |
+
},
|
906 |
+
"GAD": {
|
907 |
+
"Overall": 67.76
|
908 |
+
},
|
909 |
+
"HoC": {
|
910 |
+
"Overall": 67.76
|
911 |
+
},
|
912 |
+
"Pharma. QA": {
|
913 |
+
"Overall": 67.76
|
914 |
+
},
|
915 |
+
"Drug Inter.": {
|
916 |
+
"Overall": 67.76
|
917 |
+
}
|
918 |
+
},
|
919 |
+
"MedAlpaca": {
|
920 |
+
"META": {
|
921 |
+
"Method": [
|
922 |
+
"MedAlpaca"
|
923 |
+
],
|
924 |
+
"Parameters": "7B",
|
925 |
+
"Org": "OpenAI",
|
926 |
+
"OpenSource": "No",
|
927 |
+
"Verified": "Yes"
|
928 |
+
},
|
929 |
+
"MedQA": {
|
930 |
+
"Overall": 80.75
|
931 |
+
},
|
932 |
+
"MedMCQA": {
|
933 |
+
"Overall": 71.63
|
934 |
+
},
|
935 |
+
"MMLU-Medicine": {
|
936 |
+
"Overall": 70.17
|
937 |
+
},
|
938 |
+
"PubMedQA": {
|
939 |
+
"Overall": 67.76
|
940 |
+
},
|
941 |
+
"Referral QA": {
|
942 |
+
"Overall": 67.76
|
943 |
+
},
|
944 |
+
"Treat Recom.": {
|
945 |
+
"Overall": 67.76
|
946 |
+
},
|
947 |
+
"MIMIC": {
|
948 |
+
"Overall": 67.76
|
949 |
+
},
|
950 |
+
"IU-Xray": {
|
951 |
+
"Overall": 67.76
|
952 |
+
},
|
953 |
+
"Hospitaliz. Summari.": {
|
954 |
+
"Overall": 67.76
|
955 |
+
},
|
956 |
+
"Patient Education": {
|
957 |
+
"Overall": 67.76
|
958 |
+
},
|
959 |
+
"BC5": {
|
960 |
+
"Overall": 67.76
|
961 |
+
},
|
962 |
+
"NCBI": {
|
963 |
+
"Overall": 67.76
|
964 |
+
},
|
965 |
+
"DDI": {
|
966 |
+
"Overall": 67.76
|
967 |
+
},
|
968 |
+
"GAD": {
|
969 |
+
"Overall": 67.76
|
970 |
+
},
|
971 |
+
"HoC": {
|
972 |
+
"Overall": 67.76
|
973 |
+
},
|
974 |
+
"Pharma. QA": {
|
975 |
+
"Overall": 67.76
|
976 |
+
},
|
977 |
+
"Drug Inter.": {
|
978 |
+
"Overall": 67.76
|
979 |
+
}
|
980 |
+
},
|
981 |
+
"ClinicalCamel": {
|
982 |
+
"META": {
|
983 |
+
"Method": [
|
984 |
+
"ClinicalCamel"
|
985 |
+
],
|
986 |
+
"Parameters": "",
|
987 |
+
"Org": "OpenAI",
|
988 |
+
"OpenSource": "No",
|
989 |
+
"Verified": "Yes"
|
990 |
+
},
|
991 |
+
"MedQA": {
|
992 |
+
"Overall": 80.75
|
993 |
+
},
|
994 |
+
"MedMCQA": {
|
995 |
+
"Overall": 71.63
|
996 |
+
},
|
997 |
+
"MMLU-Medicine": {
|
998 |
+
"Overall": 70.17
|
999 |
+
},
|
1000 |
+
"PubMedQA": {
|
1001 |
+
"Overall": 67.76
|
1002 |
+
},
|
1003 |
+
"Referral QA": {
|
1004 |
+
"Overall": 67.76
|
1005 |
+
},
|
1006 |
+
"Treat Recom.": {
|
1007 |
+
"Overall": 67.76
|
1008 |
+
},
|
1009 |
+
"MIMIC": {
|
1010 |
+
"Overall": 67.76
|
1011 |
+
},
|
1012 |
+
"IU-Xray": {
|
1013 |
+
"Overall": 67.76
|
1014 |
+
},
|
1015 |
+
"Hospitaliz. Summari.": {
|
1016 |
+
"Overall": 67.76
|
1017 |
+
},
|
1018 |
+
"Patient Education": {
|
1019 |
+
"Overall": 67.76
|
1020 |
+
},
|
1021 |
+
"BC5": {
|
1022 |
+
"Overall": 67.76
|
1023 |
+
},
|
1024 |
+
"NCBI": {
|
1025 |
+
"Overall": 67.76
|
1026 |
+
},
|
1027 |
+
"DDI": {
|
1028 |
+
"Overall": 67.76
|
1029 |
+
},
|
1030 |
+
"GAD": {
|
1031 |
+
"Overall": 67.76
|
1032 |
+
},
|
1033 |
+
"HoC": {
|
1034 |
+
"Overall": 67.76
|
1035 |
+
},
|
1036 |
+
"Pharma. QA": {
|
1037 |
+
"Overall": 67.76
|
1038 |
+
},
|
1039 |
+
"Drug Inter.": {
|
1040 |
+
"Overall": 67.76
|
1041 |
+
}
|
1042 |
+
},
|
1043 |
+
"Meditron-70B": {
|
1044 |
+
"META": {
|
1045 |
+
"Method": [
|
1046 |
+
"Meditron-70B"
|
1047 |
+
],
|
1048 |
+
"Parameters": "13B",
|
1049 |
+
"Org": "Meta",
|
1050 |
+
"OpenSource": "Yes",
|
1051 |
+
"Verified": "Yes"
|
1052 |
+
},
|
1053 |
+
"Shopping Concept Understanding": {
|
1054 |
+
"Overall": 45.86
|
1055 |
+
},
|
1056 |
+
"Shopping Knowledge Reasoning": {
|
1057 |
+
"Overall": 39.47
|
1058 |
+
},
|
1059 |
+
"User Behavior Alignment": {
|
1060 |
+
"Overall": 39.43
|
1061 |
+
},
|
1062 |
+
"Multi-lingual Abilities": {
|
1063 |
+
"Overall": 44.23
|
1064 |
}
|
1065 |
},
|
1066 |
}
|