Update score.json
Browse files- score.json +187 -1045
score.json
CHANGED
@@ -1,1182 +1,324 @@
|
|
1 |
{
|
2 |
-
"llama3-llava-next-8b-hf-
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
},
|
8 |
-
"gpt-4o-
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
},
|
14 |
-
"gpt-4o-mini-
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
},
|
20 |
-
"fuyu-8b-
|
21 |
-
"
|
22 |
-
"
|
23 |
-
},
|
24 |
-
"llava-1.5-13b-hf-
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
},
|
30 |
-
"llava-1.5-7b-hf-
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
},
|
36 |
-
"llava-v1.6-mistral-7b-hf-
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
},
|
42 |
-
"llava-v1.6-vicuna-13b-hf-
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
},
|
48 |
-
"llava-v1.6-vicuna-7b-hf-
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
},
|
54 |
-
"MiniCPM-V-2_6-
|
55 |
-
"
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"
|
59 |
-
},
|
60 |
-
"
|
61 |
-
"
|
62 |
-
"
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
"
|
68 |
-
"
|
69 |
-
|
70 |
-
|
71 |
-
"
|
72 |
-
"visual-advance": 0.15,
|
73 |
-
"knowledge": 0.1206896551724138,
|
74 |
-
"reason": 0.15384615384615385,
|
75 |
-
"gui": {
|
76 |
"100": 0.65,
|
77 |
"20": 0.19,
|
78 |
"50": 0.46,
|
79 |
"200": 0.84
|
80 |
},
|
81 |
-
"
|
82 |
"100": 0.30916030534351147,
|
83 |
"20": 0.03435114503816794,
|
84 |
"50": 0.16412213740458015,
|
85 |
"200": 0.5
|
86 |
}
|
87 |
},
|
88 |
-
"molmo-72b-0924-
|
89 |
-
"
|
90 |
-
"
|
91 |
-
"
|
92 |
-
"
|
93 |
},
|
94 |
-
"mc-
|
95 |
-
"
|
96 |
-
"
|
97 |
-
"
|
98 |
-
"
|
99 |
},
|
100 |
-
"
|
101 |
-
"
|
102 |
-
"visual-advance": 0.25,
|
103 |
-
"knowledge": 0.6724137931034483,
|
104 |
-
"visual-basic": 0.11627906976744186
|
105 |
-
},
|
106 |
-
"qwen2-vl-7b-instruct-24": {
|
107 |
-
"gui": {
|
108 |
"100": 0.41,
|
109 |
"20": 0.08,
|
110 |
"200": 0.76,
|
111 |
"50": 0.21
|
112 |
},
|
113 |
-
"
|
114 |
"100": 0.40458015267175573,
|
115 |
"20": 0.13740458015267176,
|
116 |
"200": 0.5572519083969466,
|
117 |
"50": 0.25190839694656486
|
118 |
},
|
119 |
-
"
|
120 |
-
"
|
121 |
-
"
|
122 |
-
"
|
123 |
},
|
124 |
-
"llama-3.2-11b-vision-instruct-
|
125 |
-
"
|
126 |
-
"
|
127 |
-
"
|
128 |
-
"
|
129 |
},
|
130 |
-
"qwen2-vl-72b-instruct-
|
131 |
-
"
|
132 |
"100": 0.0,
|
133 |
"20": 0.0,
|
134 |
"200": 0.0,
|
135 |
"50": 0.0
|
136 |
},
|
137 |
-
"
|
138 |
"100": 0.35877862595419846,
|
139 |
"20": 0.09541984732824428,
|
140 |
"200": 0.5038167938931297,
|
141 |
"50": 0.22137404580152673
|
142 |
}
|
143 |
},
|
144 |
-
"mc-sft-llava_next_8b-mcqa_v3_12_25_277k-
|
145 |
-
"
|
146 |
-
"
|
147 |
-
"
|
148 |
-
"
|
149 |
-
},
|
150 |
-
"mc-vsft-
|
151 |
-
"
|
152 |
-
"
|
153 |
-
"
|
154 |
-
"
|
155 |
-
},
|
156 |
-
"mc-vsft-
|
157 |
-
"
|
158 |
-
"
|
159 |
-
"
|
160 |
-
"
|
161 |
-
},
|
162 |
-
"mc-sft-qwen2_vl_7b-mcqa_v3_12_25_277k-
|
163 |
-
"
|
164 |
-
"
|
165 |
-
"
|
166 |
-
"
|
167 |
-
},
|
168 |
-
"
|
169 |
-
"
|
170 |
-
"
|
171 |
-
"
|
172 |
-
"
|
173 |
-
},
|
174 |
-
"
|
175 |
-
"
|
176 |
-
"
|
177 |
-
"
|
178 |
-
"
|
179 |
-
},
|
180 |
-
"point-
|
181 |
-
"
|
182 |
-
"100": 0.65,
|
183 |
-
"20": 0.02,
|
184 |
-
"50": 0.2,
|
185 |
-
"200": 0.97
|
186 |
-
},
|
187 |
-
"embodied": {
|
188 |
-
"100": 0.4198473282442748,
|
189 |
-
"20": 0.030534351145038167,
|
190 |
-
"50": 0.16030534351145037,
|
191 |
-
"200": 0.6450381679389313
|
192 |
-
}
|
193 |
-
},
|
194 |
-
"mc-point-qwen2-vl-7b-6000+2676-250118-24": {
|
195 |
-
"gui": {
|
196 |
-
"100": 0.11,
|
197 |
-
"20": 0.0,
|
198 |
-
"50": 0.0,
|
199 |
-
"200": 0.35
|
200 |
-
},
|
201 |
-
"embodied": {
|
202 |
-
"100": 0.48091603053435117,
|
203 |
-
"20": 0.04961832061068702,
|
204 |
-
"50": 0.2099236641221374,
|
205 |
-
"200": 0.7137404580152672
|
206 |
-
}
|
207 |
-
},
|
208 |
-
"point-qwen2-vl-7b-7000-250116-24": {
|
209 |
-
"gui": {
|
210 |
-
"100": 0.19,
|
211 |
-
"20": 0.01,
|
212 |
-
"50": 0.04,
|
213 |
-
"200": 0.35
|
214 |
-
},
|
215 |
-
"embodied": {
|
216 |
-
"100": 0.4389312977099237,
|
217 |
-
"20": 0.03816793893129771,
|
218 |
-
"50": 0.16030534351145037,
|
219 |
-
"200": 0.648854961832061
|
220 |
-
}
|
221 |
-
},
|
222 |
-
"point-qwen2-vl-7b-5000-250116-24": {
|
223 |
-
"gui": {
|
224 |
-
"100": 0.0,
|
225 |
-
"20": 0.0,
|
226 |
-
"50": 0.0,
|
227 |
-
"200": 0.0
|
228 |
-
},
|
229 |
-
"embodied": {
|
230 |
-
"100": 0.1297709923664122,
|
231 |
-
"20": 0.015267175572519083,
|
232 |
-
"50": 0.08015267175572519,
|
233 |
-
"200": 0.16793893129770993
|
234 |
-
}
|
235 |
-
},
|
236 |
-
"mc-point-qwen2-vl-7b-919-250118-24": {
|
237 |
-
"gui": {
|
238 |
-
"100": 0.04,
|
239 |
-
"20": 0.0,
|
240 |
-
"50": 0.0,
|
241 |
-
"200": 0.12
|
242 |
-
},
|
243 |
-
"embodied": {
|
244 |
-
"100": 0.4312977099236641,
|
245 |
-
"20": 0.04198473282442748,
|
246 |
-
"50": 0.17938931297709923,
|
247 |
-
"200": 0.5801526717557252
|
248 |
-
}
|
249 |
-
},
|
250 |
-
"mc-point-qwen2-vl-7b-6000+1200-250118_old-24": {
|
251 |
-
"gui": {
|
252 |
-
"100": 0.21,
|
253 |
-
"20": 0.0,
|
254 |
-
"50": 0.02,
|
255 |
-
"200": 0.45
|
256 |
-
},
|
257 |
-
"embodied": {
|
258 |
-
"100": 0.41603053435114506,
|
259 |
-
"20": 0.04961832061068702,
|
260 |
-
"50": 0.183206106870229,
|
261 |
-
"200": 0.6641221374045801
|
262 |
-
}
|
263 |
-
},
|
264 |
-
"point-qwen2-vl-7b-13885-250116_old-24": {
|
265 |
-
"gui": {
|
266 |
-
"100": 0.0,
|
267 |
-
"20": 0.0,
|
268 |
-
"50": 0.0,
|
269 |
-
"200": 0.0
|
270 |
-
},
|
271 |
-
"embodied": {
|
272 |
-
"100": 0.4961832061068702,
|
273 |
-
"20": 0.03435114503816794,
|
274 |
-
"50": 0.21374045801526717,
|
275 |
-
"200": 0.6984732824427481
|
276 |
-
}
|
277 |
-
},
|
278 |
-
"mc-point-toy-qwen2-vl-7b-2812-24": {
|
279 |
-
"gui": {
|
280 |
-
"100": 0.8,
|
281 |
-
"20": 0.0,
|
282 |
-
"50": 0.36,
|
283 |
-
"200": 0.99
|
284 |
-
},
|
285 |
-
"embodied": {
|
286 |
-
"100": 0.061068702290076333,
|
287 |
-
"20": 0.0,
|
288 |
-
"50": 0.019083969465648856,
|
289 |
-
"200": 0.14885496183206107
|
290 |
-
}
|
291 |
-
},
|
292 |
-
"mc-point-toy-qwen2-vl-7b-703-24": {
|
293 |
-
"gui": {
|
294 |
-
"100": 0.74,
|
295 |
-
"20": 0.02,
|
296 |
-
"50": 0.43,
|
297 |
-
"200": 0.98
|
298 |
-
},
|
299 |
-
"embodied": {
|
300 |
-
"100": 0.12595419847328243,
|
301 |
-
"20": 0.007633587786259542,
|
302 |
-
"50": 0.03816793893129771,
|
303 |
-
"200": 0.2786259541984733
|
304 |
-
}
|
305 |
-
},
|
306 |
-
"point-qwen2-vl-7b-8000-250116-24": {
|
307 |
-
"gui": {
|
308 |
-
"100": 0.03,
|
309 |
-
"20": 0.0,
|
310 |
-
"50": 0.0,
|
311 |
-
"200": 0.03
|
312 |
-
},
|
313 |
-
"embodied": {
|
314 |
-
"100": 0.5458015267175572,
|
315 |
-
"20": 0.05343511450381679,
|
316 |
-
"50": 0.21755725190839695,
|
317 |
-
"200": 0.732824427480916
|
318 |
-
}
|
319 |
-
},
|
320 |
-
"mc-point-toy-qwen2-vl-7b-2109-24": {
|
321 |
-
"gui": {
|
322 |
-
"100": 0.81,
|
323 |
-
"20": 0.03,
|
324 |
-
"50": 0.35,
|
325 |
-
"200": 0.99
|
326 |
-
},
|
327 |
-
"embodied": {
|
328 |
-
"100": 0.05343511450381679,
|
329 |
-
"20": 0.0,
|
330 |
-
"50": 0.007633587786259542,
|
331 |
-
"200": 0.13358778625954199
|
332 |
-
}
|
333 |
-
},
|
334 |
-
"point-qwen2-vl-7b-3000-250116-24": {
|
335 |
-
"gui": {
|
336 |
-
"100": 0.04,
|
337 |
-
"20": 0.0,
|
338 |
-
"50": 0.01,
|
339 |
-
"200": 0.08
|
340 |
-
},
|
341 |
-
"embodied": {
|
342 |
-
"100": 0.3893129770992366,
|
343 |
-
"20": 0.0648854961832061,
|
344 |
-
"50": 0.2099236641221374,
|
345 |
-
"200": 0.5610687022900763
|
346 |
-
}
|
347 |
-
},
|
348 |
-
"point-qwen2-vl-7b-6000-250116-24": {
|
349 |
-
"gui": {
|
350 |
-
"100": 0.34,
|
351 |
-
"20": 0.02,
|
352 |
-
"50": 0.08,
|
353 |
-
"200": 0.57
|
354 |
-
},
|
355 |
-
"embodied": {
|
356 |
-
"100": 0.061068702290076333,
|
357 |
-
"20": 0.011450381679389313,
|
358 |
-
"50": 0.030534351145038167,
|
359 |
-
"200": 0.09923664122137404
|
360 |
-
}
|
361 |
-
},
|
362 |
-
"point-qwen2-vl-7b-9000-250116-24": {
|
363 |
-
"gui": {
|
364 |
-
"100": 0.0,
|
365 |
-
"20": 0.0,
|
366 |
-
"50": 0.0,
|
367 |
-
"200": 0.0
|
368 |
-
},
|
369 |
-
"embodied": {
|
370 |
-
"100": 0.4541984732824427,
|
371 |
-
"20": 0.03816793893129771,
|
372 |
-
"50": 0.23282442748091603,
|
373 |
-
"200": 0.6259541984732825
|
374 |
-
}
|
375 |
-
},
|
376 |
-
"point-qwen2-vl-7b-11000-250116-24": {
|
377 |
-
"gui": {
|
378 |
-
"100": 0.0,
|
379 |
-
"20": 0.0,
|
380 |
-
"50": 0.0,
|
381 |
-
"200": 0.0
|
382 |
-
},
|
383 |
-
"embodied": {
|
384 |
-
"100": 0.46946564885496184,
|
385 |
-
"20": 0.07633587786259542,
|
386 |
-
"50": 0.18702290076335878,
|
387 |
-
"200": 0.6564885496183206
|
388 |
-
}
|
389 |
-
},
|
390 |
-
"mc-point-toy-qwen2-vl-7b-175-24": {
|
391 |
-
"gui": {
|
392 |
-
"100": 0.69,
|
393 |
-
"20": 0.04,
|
394 |
-
"50": 0.44,
|
395 |
-
"200": 0.96
|
396 |
-
},
|
397 |
-
"embodied": {
|
398 |
-
"100": 0.0916030534351145,
|
399 |
-
"20": 0.007633587786259542,
|
400 |
-
"50": 0.015267175572519083,
|
401 |
-
"200": 0.19083969465648856
|
402 |
-
}
|
403 |
-
},
|
404 |
-
"mc-point-qwen2-vl-7b-300-250118-24": {
|
405 |
-
"gui": {
|
406 |
-
"100": 0.03,
|
407 |
-
"20": 0.0,
|
408 |
-
"50": 0.0,
|
409 |
-
"200": 0.08
|
410 |
-
},
|
411 |
-
"embodied": {
|
412 |
-
"100": 0.35877862595419846,
|
413 |
-
"20": 0.030534351145038167,
|
414 |
-
"50": 0.17557251908396945,
|
415 |
-
"200": 0.5038167938931297
|
416 |
-
}
|
417 |
-
},
|
418 |
-
"mc-point-qwen2-vl-7b-6000+2400-250118_old-24": {
|
419 |
-
"gui": {
|
420 |
-
"100": 0.11,
|
421 |
-
"20": 0.0,
|
422 |
-
"50": 0.0,
|
423 |
-
"200": 0.34
|
424 |
-
},
|
425 |
-
"embodied": {
|
426 |
-
"100": 0.5038167938931297,
|
427 |
-
"20": 0.05343511450381679,
|
428 |
-
"50": 0.1946564885496183,
|
429 |
-
"200": 0.683206106870229
|
430 |
-
}
|
431 |
-
},
|
432 |
-
"point-qwen2-vl-7b-13000-250116-24": {
|
433 |
-
"gui": {
|
434 |
-
"100": 0.0,
|
435 |
-
"20": 0.0,
|
436 |
-
"50": 0.0,
|
437 |
-
"200": 0.0
|
438 |
-
},
|
439 |
-
"embodied": {
|
440 |
-
"100": 0.5,
|
441 |
-
"20": 0.05725190839694656,
|
442 |
-
"50": 0.16412213740458015,
|
443 |
-
"200": 0.6679389312977099
|
444 |
-
}
|
445 |
-
},
|
446 |
-
"point-qwen2-vl-7b-12000-250116-24": {
|
447 |
-
"gui": {
|
448 |
-
"100": 0.0,
|
449 |
-
"20": 0.0,
|
450 |
-
"50": 0.0,
|
451 |
-
"200": 0.0
|
452 |
-
},
|
453 |
-
"embodied": {
|
454 |
-
"100": 0.4618320610687023,
|
455 |
-
"20": 0.030534351145038167,
|
456 |
-
"50": 0.1717557251908397,
|
457 |
-
"200": 0.6641221374045801
|
458 |
-
}
|
459 |
-
},
|
460 |
-
"point-qwen2-vl-7b-4000-250116-24": {
|
461 |
-
"gui": {
|
462 |
-
"100": 0.0,
|
463 |
-
"20": 0.0,
|
464 |
-
"50": 0.0,
|
465 |
-
"200": 0.0
|
466 |
-
},
|
467 |
-
"embodied": {
|
468 |
-
"100": 0.07251908396946564,
|
469 |
-
"20": 0.007633587786259542,
|
470 |
-
"50": 0.03816793893129771,
|
471 |
-
"200": 0.11450381679389313
|
472 |
-
}
|
473 |
-
},
|
474 |
-
"point-qwen2-vl-7b-2000-250116-24": {
|
475 |
-
"gui": {
|
476 |
-
"100": 0.02,
|
477 |
-
"20": 0.0,
|
478 |
-
"50": 0.02,
|
479 |
-
"200": 0.1
|
480 |
-
},
|
481 |
-
"embodied": {
|
482 |
-
"100": 0.3931297709923664,
|
483 |
-
"20": 0.061068702290076333,
|
484 |
-
"50": 0.183206106870229,
|
485 |
-
"200": 0.5877862595419847
|
486 |
-
}
|
487 |
-
},
|
488 |
-
"point-qwen2-vl-7b-10000-250116-24": {
|
489 |
-
"gui": {
|
490 |
-
"100": 0.0,
|
491 |
-
"20": 0.0,
|
492 |
-
"50": 0.0,
|
493 |
-
"200": 0.0
|
494 |
-
},
|
495 |
-
"embodied": {
|
496 |
-
"100": 0.48854961832061067,
|
497 |
-
"20": 0.04198473282442748,
|
498 |
-
"50": 0.20610687022900764,
|
499 |
-
"200": 0.6526717557251909
|
500 |
-
}
|
501 |
-
},
|
502 |
-
"mc-point-qwen2-vl-7b-25021002-A800-c32-e1-b8-a1_checkpoint-800-24": {
|
503 |
-
"gui": {
|
504 |
"100": 0.69,
|
505 |
"20": 0.4,
|
506 |
"200": 0.95,
|
507 |
"50": 0.51
|
508 |
},
|
509 |
-
"
|
510 |
"100": 0.6603053435114504,
|
511 |
"20": 0.22137404580152673,
|
512 |
"200": 0.7862595419847328,
|
513 |
"50": 0.4732824427480916
|
514 |
},
|
515 |
-
"
|
516 |
-
"
|
517 |
-
"
|
518 |
-
"
|
519 |
-
},
|
520 |
-
"mc-point-qwen2-vl-7b-25021002-A800-c32-e1-b8-a1_checkpoint-1000-24": {
|
521 |
-
"gui": {
|
522 |
-
"100": 0.69,
|
523 |
-
"20": 0.38,
|
524 |
-
"200": 0.96,
|
525 |
-
"50": 0.5
|
526 |
-
},
|
527 |
-
"embodied": {
|
528 |
-
"100": 0.6641221374045801,
|
529 |
-
"20": 0.25190839694656486,
|
530 |
-
"200": 0.7786259541984732,
|
531 |
-
"50": 0.48091603053435117
|
532 |
-
},
|
533 |
-
"reason": 0.3076923076923077,
|
534 |
-
"knowledge": 0.6206896551724138,
|
535 |
-
"visual-basic": 0.6046511627906976,
|
536 |
-
"visual-advance": 0.525
|
537 |
-
},
|
538 |
-
"mc-point-qwen2-vl-7b-25021002-A800-c32-e1-b8-a1_checkpoint-400-24": {
|
539 |
-
"gui": {
|
540 |
-
"100": 0.61,
|
541 |
-
"20": 0.33,
|
542 |
-
"200": 0.96,
|
543 |
-
"50": 0.5
|
544 |
-
},
|
545 |
-
"embodied": {
|
546 |
-
"100": 0.6335877862595419,
|
547 |
-
"20": 0.20229007633587787,
|
548 |
-
"200": 0.7977099236641222,
|
549 |
-
"50": 0.4389312977099237
|
550 |
-
},
|
551 |
-
"reason": 0.3076923076923077,
|
552 |
-
"knowledge": 0.7413793103448276,
|
553 |
-
"visual-basic": 0.5348837209302325,
|
554 |
-
"visual-advance": 0.45
|
555 |
-
},
|
556 |
-
"mc-point-qwen2-vl-7b-25021002-A800-c32-e1-b8-a1_checkpoint-600-24": {
|
557 |
-
"gui": {
|
558 |
-
"100": 0.67,
|
559 |
-
"20": 0.34,
|
560 |
-
"200": 0.96,
|
561 |
-
"50": 0.51
|
562 |
-
},
|
563 |
-
"embodied": {
|
564 |
-
"100": 0.6374045801526718,
|
565 |
-
"20": 0.20610687022900764,
|
566 |
-
"200": 0.7900763358778626,
|
567 |
-
"50": 0.44656488549618323
|
568 |
-
},
|
569 |
-
"reason": 0.23076923076923078,
|
570 |
-
"knowledge": 0.7068965517241379,
|
571 |
-
"visual-basic": 0.46511627906976744,
|
572 |
-
"visual-advance": 0.55
|
573 |
-
},
|
574 |
-
"mc-anneal-qwen2-vl-7b-25021003-A800-c16-e1-b8-a1_checkpoint-200-24": {
|
575 |
-
"gui": {
|
576 |
-
"100": 0.41,
|
577 |
-
"20": 0.2,
|
578 |
-
"200": 0.66,
|
579 |
-
"50": 0.29
|
580 |
-
},
|
581 |
-
"embodied": {
|
582 |
-
"100": 0.20229007633587787,
|
583 |
-
"20": 0.03816793893129771,
|
584 |
-
"200": 0.40458015267175573,
|
585 |
-
"50": 0.10305343511450382
|
586 |
-
}
|
587 |
-
},
|
588 |
-
"mc-bbox-qwen2-vl-7b-25020805-A800-c32-e1-b2-a1_checkpoint-2000-24": {
|
589 |
-
"gui": {
|
590 |
-
"100": 0.56,
|
591 |
-
"20": 0.36,
|
592 |
-
"200": 0.71,
|
593 |
-
"50": 0.45
|
594 |
-
},
|
595 |
-
"embodied": {
|
596 |
-
"100": 0.08015267175572519,
|
597 |
-
"20": 0.022900763358778626,
|
598 |
-
"200": 0.14885496183206107,
|
599 |
-
"50": 0.03816793893129771
|
600 |
-
}
|
601 |
-
},
|
602 |
-
"mc-bbox-qwen2-vl-7b-25020805-A800-c32-e1-b2-a1_checkpoint-400-24": {
|
603 |
-
"gui": {
|
604 |
-
"100": 0.52,
|
605 |
-
"20": 0.23,
|
606 |
-
"200": 0.84,
|
607 |
-
"50": 0.36
|
608 |
-
},
|
609 |
-
"embodied": {
|
610 |
-
"100": 0.12213740458015267,
|
611 |
-
"20": 0.019083969465648856,
|
612 |
-
"200": 0.1984732824427481,
|
613 |
-
"50": 0.0648854961832061
|
614 |
-
}
|
615 |
},
|
616 |
-
"mc-bbox-
|
617 |
-
"
|
618 |
"100": 0.57,
|
619 |
"20": 0.38,
|
620 |
"200": 0.74,
|
621 |
"50": 0.47
|
622 |
},
|
623 |
-
"
|
624 |
"100": 0.0916030534351145,
|
625 |
"20": 0.015267175572519083,
|
626 |
"200": 0.15648854961832062,
|
627 |
"50": 0.03435114503816794
|
628 |
}
|
629 |
},
|
630 |
-
"mc-
|
631 |
-
"
|
632 |
-
"100": 0.55,
|
633 |
-
"20": 0.33,
|
634 |
-
"200": 0.72,
|
635 |
-
"50": 0.47
|
636 |
-
},
|
637 |
-
"embodied": {
|
638 |
-
"100": 0.0916030534351145,
|
639 |
-
"20": 0.019083969465648856,
|
640 |
-
"200": 0.16412213740458015,
|
641 |
-
"50": 0.04198473282442748
|
642 |
-
}
|
643 |
-
},
|
644 |
-
"mc-bbox-qwen2-vl-7b-25020805-A800-c32-e1-b2-a1_checkpoint-2800-24": {
|
645 |
-
"gui": {
|
646 |
-
"100": 0.56,
|
647 |
-
"20": 0.36,
|
648 |
-
"200": 0.72,
|
649 |
-
"50": 0.45
|
650 |
-
},
|
651 |
-
"embodied": {
|
652 |
-
"100": 0.09923664122137404,
|
653 |
-
"20": 0.019083969465648856,
|
654 |
-
"200": 0.16412213740458015,
|
655 |
-
"50": 0.04198473282442748
|
656 |
-
}
|
657 |
-
},
|
658 |
-
"mc-bbox-qwen2-vl-7b-25020805-A800-c32-e1-b2-a1_checkpoint-1200-24": {
|
659 |
-
"gui": {
|
660 |
-
"100": 0.51,
|
661 |
-
"20": 0.32,
|
662 |
-
"200": 0.66,
|
663 |
-
"50": 0.43
|
664 |
-
},
|
665 |
-
"embodied": {
|
666 |
-
"100": 0.09541984732824428,
|
667 |
-
"20": 0.030534351145038167,
|
668 |
-
"200": 0.1717557251908397,
|
669 |
-
"50": 0.05725190839694656
|
670 |
-
}
|
671 |
-
},
|
672 |
-
"mc-bbox-qwen2-vl-7b-25020805-A800-c32-e1-b2-a1_checkpoint-1600-24": {
|
673 |
-
"gui": {
|
674 |
-
"100": 0.53,
|
675 |
-
"20": 0.26,
|
676 |
-
"200": 0.67,
|
677 |
-
"50": 0.41
|
678 |
-
},
|
679 |
-
"embodied": {
|
680 |
-
"100": 0.0916030534351145,
|
681 |
-
"20": 0.022900763358778626,
|
682 |
-
"200": 0.1717557251908397,
|
683 |
-
"50": 0.04198473282442748
|
684 |
-
}
|
685 |
-
},
|
686 |
-
"mc-bbox-qwen2-vl-7b-25020805-A800-c32-e1-b2-a1_checkpoint-800-24": {
|
687 |
-
"gui": {
|
688 |
-
"100": 0.48,
|
689 |
-
"20": 0.23,
|
690 |
-
"200": 0.7,
|
691 |
-
"50": 0.35
|
692 |
-
},
|
693 |
-
"embodied": {
|
694 |
-
"100": 0.12213740458015267,
|
695 |
-
"20": 0.03435114503816794,
|
696 |
-
"200": 0.24427480916030533,
|
697 |
-
"50": 0.06870229007633588
|
698 |
-
}
|
699 |
-
},
|
700 |
-
"mc-point-qwen2-vl-7b-6000+1200-250118-24": {
|
701 |
-
"gui": {
|
702 |
-
"100": 0.2,
|
703 |
-
"20": 0.0,
|
704 |
-
"200": 0.48,
|
705 |
-
"50": 0.03
|
706 |
-
},
|
707 |
-
"embodied": {
|
708 |
-
"100": 0.6374045801526718,
|
709 |
-
"20": 0.05725190839694656,
|
710 |
-
"200": 0.8015267175572519,
|
711 |
-
"50": 0.2900763358778626
|
712 |
-
}
|
713 |
-
},
|
714 |
-
"mc-point-qwen2-vl-7b-6000+1800-250118-24": {
|
715 |
-
"gui": {
|
716 |
-
"100": 0.17,
|
717 |
-
"20": 0.0,
|
718 |
-
"200": 0.44,
|
719 |
-
"50": 0.02
|
720 |
-
},
|
721 |
-
"embodied": {
|
722 |
-
"100": 0.6145038167938931,
|
723 |
-
"20": 0.04198473282442748,
|
724 |
-
"200": 0.7862595419847328,
|
725 |
-
"50": 0.183206106870229
|
726 |
-
}
|
727 |
-
},
|
728 |
-
"mc-point-qwen2-vl-7b-6000+2400-250118-24": {
|
729 |
-
"gui": {
|
730 |
-
"100": 0.13,
|
731 |
-
"20": 0.0,
|
732 |
-
"200": 0.39,
|
733 |
-
"50": 0.0
|
734 |
-
},
|
735 |
-
"embodied": {
|
736 |
-
"100": 0.6221374045801527,
|
737 |
-
"20": 0.04961832061068702,
|
738 |
-
"200": 0.7900763358778626,
|
739 |
-
"50": 0.1984732824427481
|
740 |
-
}
|
741 |
-
},
|
742 |
-
"point-qwen2-vl-7b-1000-250116-24": {
|
743 |
-
"gui": {
|
744 |
-
"100": 0.63,
|
745 |
-
"20": 0.02,
|
746 |
-
"200": 0.96,
|
747 |
-
"50": 0.19
|
748 |
-
},
|
749 |
-
"embodied": {
|
750 |
-
"100": 0.5458015267175572,
|
751 |
-
"20": 0.0916030534351145,
|
752 |
-
"200": 0.7061068702290076,
|
753 |
-
"50": 0.29770992366412213
|
754 |
-
}
|
755 |
-
},
|
756 |
-
"point-qwen2-vl-7b-13885-250116-24": {
|
757 |
-
"gui": {
|
758 |
-
"100": 0.09,
|
759 |
-
"20": 0.01,
|
760 |
-
"200": 0.2,
|
761 |
-
"50": 0.01
|
762 |
-
},
|
763 |
-
"embodied": {
|
764 |
-
"100": 0.6221374045801527,
|
765 |
-
"20": 0.061068702290076333,
|
766 |
-
"200": 0.7938931297709924,
|
767 |
-
"50": 0.1984732824427481
|
768 |
-
}
|
769 |
-
},
|
770 |
-
"point-qwen2-7b-step_6000-250113-24": {
|
771 |
-
"gui": {
|
772 |
-
"100": 0.46,
|
773 |
-
"20": 0.14,
|
774 |
-
"200": 0.84,
|
775 |
-
"50": 0.19
|
776 |
-
},
|
777 |
-
"embodied": {
|
778 |
-
"100": 0.026717557251908396,
|
779 |
-
"20": 0.0,
|
780 |
-
"200": 0.10687022900763359,
|
781 |
-
"50": 0.003816793893129771
|
782 |
-
}
|
783 |
-
},
|
784 |
-
"mc-point-qwen2-vl-7b-25021002-A800-c32-e1-b8-a1checkpoint-1123-24": {
|
785 |
-
"gui": {
|
786 |
-
"100": 0.73,
|
787 |
-
"20": 0.39,
|
788 |
-
"200": 0.95,
|
789 |
-
"50": 0.51
|
790 |
-
},
|
791 |
-
"embodied": {
|
792 |
-
"100": 0.6755725190839694,
|
793 |
-
"20": 0.26717557251908397,
|
794 |
-
"200": 0.7862595419847328,
|
795 |
-
"50": 0.4732824427480916
|
796 |
-
},
|
797 |
-
"reason": 0.3076923076923077,
|
798 |
-
"knowledge": 0.6379310344827587,
|
799 |
-
"visual-basic": 0.4186046511627907,
|
800 |
-
"visual-advance": 0.25
|
801 |
-
},
|
802 |
-
"qwen2-vl-2b-instruct-24": {
|
803 |
-
"gui": {
|
804 |
-
"100": 0.0,
|
805 |
-
"20": 0.0,
|
806 |
-
"200": 0.01,
|
807 |
-
"50": 0.0
|
808 |
-
},
|
809 |
-
"embodied": {
|
810 |
-
"100": 0.0,
|
811 |
-
"20": 0.0,
|
812 |
-
"200": 0.0,
|
813 |
-
"50": 0.0
|
814 |
-
}
|
815 |
-
},
|
816 |
-
"anneal-vla-qwen2-vl-7b-250211-A800-c32-e1-b4-a1-24": {
|
817 |
-
"gui": {
|
818 |
-
"100": 0.43,
|
819 |
-
"20": 0.06,
|
820 |
-
"200": 0.93,
|
821 |
-
"50": 0.17
|
822 |
-
},
|
823 |
-
"embodied": {
|
824 |
-
"100": 0.24045801526717558,
|
825 |
-
"20": 0.019083969465648856,
|
826 |
-
"200": 0.6183206106870229,
|
827 |
-
"50": 0.08778625954198473
|
828 |
-
},
|
829 |
-
"reason": 0.46153846153846156,
|
830 |
-
"knowledge": 0.6896551724137931,
|
831 |
-
"visual-basic": 0.4186046511627907,
|
832 |
-
"visual-advance": 0.45
|
833 |
-
},
|
834 |
-
"anneal-point-qwen2-vl-7b-250211-A800-c32-e1-b4-a1-24": {
|
835 |
-
"gui": {
|
836 |
"100": 0.74,
|
837 |
"20": 0.38,
|
838 |
"200": 0.93,
|
839 |
"50": 0.56
|
840 |
},
|
841 |
-
"
|
842 |
"100": 0.648854961832061,
|
843 |
"20": 0.2099236641221374,
|
844 |
"200": 0.7786259541984732,
|
845 |
"50": 0.4618320610687023
|
846 |
},
|
847 |
-
"
|
848 |
-
"
|
849 |
-
"
|
850 |
-
"
|
851 |
},
|
852 |
-
"mc-
|
853 |
-
"
|
854 |
-
"100": 0.85,
|
855 |
-
"20": 0.67,
|
856 |
-
"200": 0.98,
|
857 |
-
"50": 0.75
|
858 |
-
},
|
859 |
-
"embodied": {
|
860 |
-
"100": 0.5114503816793893,
|
861 |
-
"20": 0.09923664122137404,
|
862 |
-
"200": 0.7442748091603053,
|
863 |
-
"50": 0.32061068702290074
|
864 |
-
},
|
865 |
-
"knowledge": 0.7586206896551724,
|
866 |
-
"visual-basic": 0.5581395348837209,
|
867 |
-
"visual-advance": 0.4,
|
868 |
-
"reason": 0.5384615384615384
|
869 |
-
},
|
870 |
-
"mc-qwen2-vl-7b-250215-A800-c32-e1-b4-a1checkpoint-800-24": {
|
871 |
-
"gui": {
|
872 |
-
"100": 0.87,
|
873 |
-
"20": 0.7,
|
874 |
-
"200": 0.98,
|
875 |
-
"50": 0.79
|
876 |
-
},
|
877 |
-
"embodied": {
|
878 |
-
"100": 0.5458015267175572,
|
879 |
-
"20": 0.1450381679389313,
|
880 |
-
"200": 0.767175572519084,
|
881 |
-
"50": 0.35877862595419846
|
882 |
-
},
|
883 |
-
"knowledge": 0.7068965517241379,
|
884 |
-
"visual-basic": 0.5581395348837209,
|
885 |
-
"visual-advance": 0.5,
|
886 |
-
"reason": 0.38461538461538464
|
887 |
-
},
|
888 |
-
"mc-qwen2-vl-7b-250215-A800-c32-e1-b4-a1checkpoint-1600-24": {
|
889 |
-
"gui": {
|
890 |
-
"100": 0.84,
|
891 |
-
"20": 0.73,
|
892 |
-
"200": 0.97,
|
893 |
-
"50": 0.82
|
894 |
-
},
|
895 |
-
"embodied": {
|
896 |
-
"100": 0.6145038167938931,
|
897 |
-
"20": 0.183206106870229,
|
898 |
-
"200": 0.7786259541984732,
|
899 |
-
"50": 0.4083969465648855
|
900 |
-
},
|
901 |
-
"knowledge": 0.6896551724137931,
|
902 |
-
"visual-basic": 0.6046511627906976,
|
903 |
-
"visual-advance": 0.45,
|
904 |
-
"reason": 0.46153846153846156
|
905 |
-
},
|
906 |
-
"mc-qwen2-vl-7b-250215-A800-c32-e1-b4-a1checkpoint-2400-24": {
|
907 |
-
"gui": {
|
908 |
"100": 0.92,
|
909 |
"20": 0.79,
|
910 |
"200": 0.99,
|
911 |
"50": 0.88
|
912 |
},
|
913 |
-
"
|
914 |
"100": 0.6068702290076335,
|
915 |
"20": 0.2099236641221374,
|
916 |
"200": 0.7824427480916031,
|
917 |
"50": 0.41603053435114506
|
918 |
},
|
919 |
-
"
|
920 |
-
"
|
921 |
-
"
|
922 |
-
"
|
923 |
},
|
924 |
-
"mc-
|
925 |
-
"
|
926 |
"100": 0.93,
|
927 |
"20": 0.84,
|
928 |
"200": 0.99,
|
929 |
"50": 0.9
|
930 |
},
|
931 |
-
"
|
932 |
"100": 0.6259541984732825,
|
933 |
"20": 0.24427480916030533,
|
934 |
"200": 0.7748091603053435,
|
935 |
"50": 0.46946564885496184
|
936 |
},
|
937 |
-
"
|
938 |
-
"
|
939 |
-
"
|
940 |
-
"
|
941 |
-
},
|
942 |
-
"mc-qwen2-vl-7b-250215-A800-c32-e1-b4-a1checkpoint-4000-24": {
|
943 |
-
"gui": {
|
944 |
-
"100": 0.92,
|
945 |
-
"20": 0.83,
|
946 |
-
"200": 0.98,
|
947 |
-
"50": 0.88
|
948 |
-
},
|
949 |
-
"embodied": {
|
950 |
-
"100": 0.6145038167938931,
|
951 |
-
"20": 0.22900763358778625,
|
952 |
-
"200": 0.7786259541984732,
|
953 |
-
"50": 0.4580152671755725
|
954 |
-
},
|
955 |
-
"knowledge": 0.7068965517241379,
|
956 |
-
"visual-basic": 0.6744186046511628,
|
957 |
-
"visual-advance": 0.55,
|
958 |
-
"reason": 0.46153846153846156
|
959 |
-
},
|
960 |
-
"mc-point-qwen2-vl-2b-250217-A800-c32-e1-b4-a1_checkpoint-800-24": {
|
961 |
-
"gui": {
|
962 |
-
"100": 0.52,
|
963 |
-
"20": 0.32,
|
964 |
-
"200": 0.9,
|
965 |
-
"50": 0.4
|
966 |
-
},
|
967 |
-
"embodied": {
|
968 |
-
"100": 0.42748091603053434,
|
969 |
-
"20": 0.0916030534351145,
|
970 |
-
"200": 0.6717557251908397,
|
971 |
-
"50": 0.27099236641221375
|
972 |
-
},
|
973 |
-
"knowledge": 0.3103448275862069,
|
974 |
-
"visual-basic": 0.5116279069767442,
|
975 |
-
"visual-advance": 0.4,
|
976 |
-
"reason": 0.15384615384615385
|
977 |
},
|
978 |
-
"mc-
|
979 |
-
"
|
980 |
"100": 0.54,
|
981 |
"20": 0.32,
|
982 |
"200": 0.93,
|
983 |
"50": 0.38
|
984 |
},
|
985 |
-
"
|
986 |
"100": 0.5038167938931297,
|
987 |
"20": 0.08015267175572519,
|
988 |
"200": 0.7175572519083969,
|
989 |
"50": 0.2748091603053435
|
990 |
},
|
991 |
-
"
|
992 |
-
"
|
993 |
-
"
|
994 |
-
"
|
995 |
-
},
|
996 |
-
"mc-point-qwen2-vl-2b-250217-A800-c32-e1-b4-a1_checkpoint-2400-24": {
|
997 |
-
"gui": {
|
998 |
-
"100": 0.56,
|
999 |
-
"20": 0.34,
|
1000 |
-
"200": 0.94,
|
1001 |
-
"50": 0.4
|
1002 |
-
},
|
1003 |
-
"embodied": {
|
1004 |
-
"100": 0.4961832061068702,
|
1005 |
-
"20": 0.14885496183206107,
|
1006 |
-
"200": 0.7480916030534351,
|
1007 |
-
"50": 0.31679389312977096
|
1008 |
-
}
|
1009 |
-
},
|
1010 |
-
"mc-point-qwen2-vl-2b-250217-A800-c32-e1-b4-a1_checkpoint-3200-24": {
|
1011 |
-
"gui": {
|
1012 |
-
"100": 0.54,
|
1013 |
-
"20": 0.4,
|
1014 |
-
"200": 0.96,
|
1015 |
-
"50": 0.44
|
1016 |
-
},
|
1017 |
-
"embodied": {
|
1018 |
-
"100": 0.5381679389312977,
|
1019 |
-
"20": 0.15648854961832062,
|
1020 |
-
"200": 0.7480916030534351,
|
1021 |
-
"50": 0.3549618320610687
|
1022 |
-
}
|
1023 |
},
|
1024 |
-
"mc-
|
1025 |
-
"
|
1026 |
"100": 0.59,
|
1027 |
"20": 0.39,
|
1028 |
"200": 0.94,
|
1029 |
"50": 0.45
|
1030 |
},
|
1031 |
-
"
|
1032 |
"100": 0.5305343511450382,
|
1033 |
"20": 0.16793893129770993,
|
1034 |
"200": 0.7557251908396947,
|
1035 |
"50": 0.3473282442748092
|
1036 |
}
|
1037 |
},
|
1038 |
-
"mc-
|
1039 |
-
"
|
1040 |
"100": 0.74,
|
1041 |
"20": 0.6,
|
1042 |
"200": 0.99,
|
1043 |
"50": 0.68
|
1044 |
},
|
1045 |
-
"
|
1046 |
"100": 0.6259541984732825,
|
1047 |
"20": 0.15267175572519084,
|
1048 |
"200": 0.7748091603053435,
|
1049 |
"50": 0.4122137404580153
|
1050 |
},
|
1051 |
-
"
|
1052 |
-
"
|
1053 |
-
"
|
1054 |
-
"
|
1055 |
-
},
|
1056 |
-
"mc-llava-next-vicuna-13b-250217-A800-c32-e1-b4-a1_checkpoint-3200-24": {
|
1057 |
-
"gui": {
|
1058 |
-
"100": 0.77,
|
1059 |
-
"20": 0.58,
|
1060 |
-
"200": 0.99,
|
1061 |
-
"50": 0.69
|
1062 |
-
},
|
1063 |
-
"embodied": {
|
1064 |
-
"100": 0.6412213740458015,
|
1065 |
-
"20": 0.14122137404580154,
|
1066 |
-
"200": 0.7862595419847328,
|
1067 |
-
"50": 0.3931297709923664
|
1068 |
-
},
|
1069 |
-
"knowledge": 0.6551724137931034,
|
1070 |
-
"visual-basic": 0.4883720930232558,
|
1071 |
-
"visual-advance": 0.45,
|
1072 |
-
"reason": 0.3076923076923077
|
1073 |
-
},
|
1074 |
-
"mc-llava-next-vicuna-13b-250217-A800-c32-e1-b4-a1_checkpoint-2400-24": {
|
1075 |
-
"gui": {
|
1076 |
-
"100": 0.75,
|
1077 |
-
"20": 0.49,
|
1078 |
-
"200": 0.98,
|
1079 |
-
"50": 0.67
|
1080 |
-
},
|
1081 |
-
"embodied": {
|
1082 |
-
"100": 0.6030534351145038,
|
1083 |
-
"20": 0.13740458015267176,
|
1084 |
-
"200": 0.767175572519084,
|
1085 |
-
"50": 0.3702290076335878
|
1086 |
-
},
|
1087 |
-
"knowledge": 0.6206896551724138,
|
1088 |
-
"visual-basic": 0.5348837209302325,
|
1089 |
-
"visual-advance": 0.45,
|
1090 |
-
"reason": 0.3076923076923077
|
1091 |
-
},
|
1092 |
-
"mc-llava-next-vicuna-13b-250217-A800-c32-e1-b4-a1_checkpoint-1600-24": {
|
1093 |
-
"gui": {
|
1094 |
-
"100": 0.76,
|
1095 |
-
"20": 0.33,
|
1096 |
-
"200": 1.0,
|
1097 |
-
"50": 0.65
|
1098 |
-
},
|
1099 |
-
"embodied": {
|
1100 |
-
"100": 0.5687022900763359,
|
1101 |
-
"20": 0.12213740458015267,
|
1102 |
-
"200": 0.7748091603053435,
|
1103 |
-
"50": 0.366412213740458
|
1104 |
-
},
|
1105 |
-
"knowledge": 0.5689655172413793,
|
1106 |
-
"visual-basic": 0.5581395348837209,
|
1107 |
-
"visual-advance": 0.35,
|
1108 |
-
"reason": 0.3076923076923077
|
1109 |
-
},
|
1110 |
-
"mc-llava-next-vicuna-13b-250217-A800-c32-e1-b4-a1_checkpoint-800-24": {
|
1111 |
-
"gui": {
|
1112 |
-
"100": 0.74,
|
1113 |
-
"20": 0.07,
|
1114 |
-
"200": 0.93,
|
1115 |
-
"50": 0.42
|
1116 |
-
},
|
1117 |
-
"embodied": {
|
1118 |
-
"100": 0.5305343511450382,
|
1119 |
-
"20": 0.08015267175572519,
|
1120 |
-
"200": 0.7709923664122137,
|
1121 |
-
"50": 0.31297709923664124
|
1122 |
-
},
|
1123 |
-
"knowledge": 0.5344827586206896,
|
1124 |
-
"visual-basic": 0.4883720930232558,
|
1125 |
-
"visual-advance": 0.4,
|
1126 |
-
"reason": 0.38461538461538464
|
1127 |
-
},
|
1128 |
-
"mc-reason-qwen2-vl-7b-250224-A800-c32-e1-b4-a1_checkpoint-800-24": {
|
1129 |
-
"gui": {
|
1130 |
-
"100": 0.0,
|
1131 |
-
"20": 0.0,
|
1132 |
-
"200": 0.0,
|
1133 |
-
"50": 0.0
|
1134 |
-
},
|
1135 |
-
"embodied": {
|
1136 |
-
"100": 0.0,
|
1137 |
-
"20": 0.0,
|
1138 |
-
"200": 0.0,
|
1139 |
-
"50": 0.0
|
1140 |
-
},
|
1141 |
-
"knowledge": 0.603448275862069,
|
1142 |
-
"visual-basic": 0.5813953488372093,
|
1143 |
-
"visual-advance": 0.45,
|
1144 |
-
"reason": 0.42528735632183906
|
1145 |
-
},
|
1146 |
-
"mc-reason-qwen2-vl-7b-250224-A800-c32-e1-b4-a1_checkpoint-1600-24": {
|
1147 |
-
"gui": {
|
1148 |
-
"100": 0.0,
|
1149 |
-
"20": 0.0,
|
1150 |
-
"200": 0.0,
|
1151 |
-
"50": 0.0
|
1152 |
-
},
|
1153 |
-
"embodied": {
|
1154 |
-
"100": 0.0,
|
1155 |
-
"20": 0.0,
|
1156 |
-
"200": 0.003816793893129771,
|
1157 |
-
"50": 0.0
|
1158 |
-
},
|
1159 |
-
"knowledge": 0.6379310344827587,
|
1160 |
-
"visual-basic": 0.5813953488372093,
|
1161 |
-
"visual-advance": 0.3,
|
1162 |
-
"reason": 0.45977011494252873
|
1163 |
},
|
1164 |
-
"mc-reason-
|
1165 |
-
"
|
1166 |
"100": 0.0,
|
1167 |
"20": 0.0,
|
1168 |
"200": 0.0,
|
1169 |
"50": 0.0
|
1170 |
},
|
1171 |
-
"
|
1172 |
"100": 0.0,
|
1173 |
"20": 0.0,
|
1174 |
"200": 0.003816793893129771,
|
1175 |
"50": 0.0
|
1176 |
},
|
1177 |
-
"
|
1178 |
-
"
|
1179 |
-
"
|
1180 |
-
"
|
1181 |
}
|
1182 |
}
|
|
|
1 |
{
|
2 |
+
"llama3-llava-next-8b-hf-2412": {
|
3 |
+
"VQA": 0.4186046511627907,
|
4 |
+
"QA": 0.1896551724137931,
|
5 |
+
"Reason": 0.23076923076923078,
|
6 |
+
"VQA_Reasoning": 0.25
|
7 |
+
},
|
8 |
+
"gpt-4o-2412": {
|
9 |
+
"QA": 0.9655172413793104,
|
10 |
+
"Reason": 0.7692307692307693,
|
11 |
+
"VQA_Reasoning": 0.85,
|
12 |
+
"VQA": 0.7674418604651163
|
13 |
+
},
|
14 |
+
"gpt-4o-mini-2412": {
|
15 |
+
"QA": 0.7586206896551724,
|
16 |
+
"Reason": 0.5384615384615384,
|
17 |
+
"VQA_Reasoning": 0.6,
|
18 |
+
"VQA": 0.627906976744186
|
19 |
+
},
|
20 |
+
"fuyu-8b-2412": {
|
21 |
+
"Reason": 0.0,
|
22 |
+
"QA": 0.017241379310344827
|
23 |
+
},
|
24 |
+
"llava-1.5-13b-hf-2412": {
|
25 |
+
"Reason": 0.0,
|
26 |
+
"VQA": 0.3023255813953488,
|
27 |
+
"QA": 0.0,
|
28 |
+
"VQA_Reasoning": 0.65
|
29 |
+
},
|
30 |
+
"llava-1.5-7b-hf-2412": {
|
31 |
+
"VQA_Reasoning": 0.45,
|
32 |
+
"VQA": 0.32558139534883723,
|
33 |
+
"Reason": 0.0,
|
34 |
+
"QA": 0.0
|
35 |
+
},
|
36 |
+
"llava-v1.6-mistral-7b-hf-2412": {
|
37 |
+
"VQA": 0.37209302325581395,
|
38 |
+
"VQA_Reasoning": 0.55,
|
39 |
+
"Reason": 0.15384615384615385,
|
40 |
+
"QA": 0.15517241379310345
|
41 |
+
},
|
42 |
+
"llava-v1.6-vicuna-13b-hf-2412": {
|
43 |
+
"VQA_Reasoning": 0.35,
|
44 |
+
"VQA": 0.4186046511627907,
|
45 |
+
"QA": 0.1724137931034483,
|
46 |
+
"Reason": 0.15384615384615385
|
47 |
+
},
|
48 |
+
"llava-v1.6-vicuna-7b-hf-2412": {
|
49 |
+
"Reason": 0.15384615384615385,
|
50 |
+
"VQA": 0.23255813953488372,
|
51 |
+
"VQA_Reasoning": 0.2,
|
52 |
+
"QA": 0.06896551724137931
|
53 |
+
},
|
54 |
+
"MiniCPM-V-2_6-2412": {
|
55 |
+
"Reason": 0.15384615384615385,
|
56 |
+
"VQA": 0.5116279069767442,
|
57 |
+
"VQA_Reasoning": 0.4,
|
58 |
+
"QA": 0.15517241379310345
|
59 |
+
},
|
60 |
+
"llava-gemma-2b-2412": {
|
61 |
+
"Reason": 0.0,
|
62 |
+
"VQA": 0.3023255813953488,
|
63 |
+
"VQA_Reasoning": 0.2,
|
64 |
+
"QA": 0.034482758620689655
|
65 |
+
},
|
66 |
+
"molmo-7b-d-0924-2412": {
|
67 |
+
"VQA": 0.5813953488372093,
|
68 |
+
"VQA_Reasoning": 0.15,
|
69 |
+
"QA": 0.1206896551724138,
|
70 |
+
"Reason": 0.15384615384615385,
|
71 |
+
"Gui_Grounding": {
|
|
|
|
|
|
|
|
|
72 |
"100": 0.65,
|
73 |
"20": 0.19,
|
74 |
"50": 0.46,
|
75 |
"200": 0.84
|
76 |
},
|
77 |
+
"Embodied_Grounding": {
|
78 |
"100": 0.30916030534351147,
|
79 |
"20": 0.03435114503816794,
|
80 |
"50": 0.16412213740458015,
|
81 |
"200": 0.5
|
82 |
}
|
83 |
},
|
84 |
+
"molmo-72b-0924-2412": {
|
85 |
+
"Reason": 0.46153846153846156,
|
86 |
+
"VQA_Reasoning": 0.55,
|
87 |
+
"QA": 0.3620689655172414,
|
88 |
+
"VQA": 0.5581395348837209
|
89 |
},
|
90 |
+
"mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2411": {
|
91 |
+
"Reason": 0.23076923076923078,
|
92 |
+
"VQA_Reasoning": 0.25,
|
93 |
+
"QA": 0.6724137931034483,
|
94 |
+
"VQA": 0.11627906976744186
|
95 |
},
|
96 |
+
"qwen2-vl-7b-instruct-2412": {
|
97 |
+
"Gui_Grounding": {
|
|
|
|
|
|
|
|
|
|
|
|
|
98 |
"100": 0.41,
|
99 |
"20": 0.08,
|
100 |
"200": 0.76,
|
101 |
"50": 0.21
|
102 |
},
|
103 |
+
"Embodied_Grounding": {
|
104 |
"100": 0.40458015267175573,
|
105 |
"20": 0.13740458015267176,
|
106 |
"200": 0.5572519083969466,
|
107 |
"50": 0.25190839694656486
|
108 |
},
|
109 |
+
"QA": 0.06896551724137931,
|
110 |
+
"VQA": 0.4186046511627907,
|
111 |
+
"VQA_Reasoning": 0.375,
|
112 |
+
"Reason": 0.15384615384615385
|
113 |
},
|
114 |
+
"llama-3.2-11b-vision-instruct-2412": {
|
115 |
+
"VQA": 0.4418604651162791,
|
116 |
+
"VQA_Reasoning": 0.25,
|
117 |
+
"Reason": 0.23076923076923078,
|
118 |
+
"QA": 0.20689655172413793
|
119 |
},
|
120 |
+
"qwen2-vl-72b-instruct-2412": {
|
121 |
+
"Gui_Grounding": {
|
122 |
"100": 0.0,
|
123 |
"20": 0.0,
|
124 |
"200": 0.0,
|
125 |
"50": 0.0
|
126 |
},
|
127 |
+
"Embodied_Grounding": {
|
128 |
"100": 0.35877862595419846,
|
129 |
"20": 0.09541984732824428,
|
130 |
"200": 0.5038167938931297,
|
131 |
"50": 0.22137404580152673
|
132 |
}
|
133 |
},
|
134 |
+
"mc-sft-llava_next_8b-mcqa_v3_12_25_277k-2412": {
|
135 |
+
"QA": 0.6724137931034483,
|
136 |
+
"Reason": 0.38461538461538464,
|
137 |
+
"VQA": 0.20930232558139536,
|
138 |
+
"VQA_Reasoning": 0.45
|
139 |
+
},
|
140 |
+
"mc-vsft-llama3_llava_next_8b-mcvqa_v4_11_21_80k-2412": {
|
141 |
+
"QA": 0.603448275862069,
|
142 |
+
"Reason": 0.3076923076923077,
|
143 |
+
"VQA": 0.5581395348837209,
|
144 |
+
"VQA_Reasoning": 0.55
|
145 |
+
},
|
146 |
+
"mc-vsft-llava_v1.6_vicuna_13b-mcvqa_v4_11_21_80k-2412": {
|
147 |
+
"QA": 0.6206896551724138,
|
148 |
+
"Reason": 0.5384615384615384,
|
149 |
+
"VQA": 0.7441860465116279,
|
150 |
+
"VQA_Reasoning": 0.7
|
151 |
+
},
|
152 |
+
"mc-sft-qwen2_vl_7b-mcqa_v3_12_25_277k-2412": {
|
153 |
+
"QA": 0.6551724137931034,
|
154 |
+
"VQA_Reasoning": 0.45,
|
155 |
+
"Reason": 0.38461538461538464,
|
156 |
+
"VQA": 0.46511627906976744
|
157 |
+
},
|
158 |
+
"mc-vsft-qwen2_vl_7b-2412": {
|
159 |
+
"VQA": 0.6511627906976745,
|
160 |
+
"Reason": 0.23076923076923078,
|
161 |
+
"QA": 0.6206896551724138,
|
162 |
+
"VQA_Reasoning": 0.75
|
163 |
+
},
|
164 |
+
"mc-vsft-qwen2_vl_2b-2412": {
|
165 |
+
"Reason": 0.15384615384615385,
|
166 |
+
"VQA_Reasoning": 0.7,
|
167 |
+
"VQA": 0.5813953488372093,
|
168 |
+
"QA": 0.1724137931034483
|
169 |
+
},
|
170 |
+
"mc-point-qwen2_vl_7b-2502": {
|
171 |
+
"Gui_Grounding": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
172 |
"100": 0.69,
|
173 |
"20": 0.4,
|
174 |
"200": 0.95,
|
175 |
"50": 0.51
|
176 |
},
|
177 |
+
"Embodied_Grounding": {
|
178 |
"100": 0.6603053435114504,
|
179 |
"20": 0.22137404580152673,
|
180 |
"200": 0.7862595419847328,
|
181 |
"50": 0.4732824427480916
|
182 |
},
|
183 |
+
"Reason": 0.38461538461538464,
|
184 |
+
"QA": 0.6724137931034483,
|
185 |
+
"VQA": 0.5116279069767442,
|
186 |
+
"VQA_Reasoning": 0.475
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
187 |
},
|
188 |
+
"mc-bbox-qwen2_vl_7b-2502": {
|
189 |
+
"Gui_Grounding": {
|
190 |
"100": 0.57,
|
191 |
"20": 0.38,
|
192 |
"200": 0.74,
|
193 |
"50": 0.47
|
194 |
},
|
195 |
+
"Embodied_Grounding": {
|
196 |
"100": 0.0916030534351145,
|
197 |
"20": 0.015267175572519083,
|
198 |
"200": 0.15648854961832062,
|
199 |
"50": 0.03435114503816794
|
200 |
}
|
201 |
},
|
202 |
+
"mc-base-qwen2_vl_7b-2502": {
|
203 |
+
"Gui_Grounding": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
204 |
"100": 0.74,
|
205 |
"20": 0.38,
|
206 |
"200": 0.93,
|
207 |
"50": 0.56
|
208 |
},
|
209 |
+
"Embodied_Grounding": {
|
210 |
"100": 0.648854961832061,
|
211 |
"20": 0.2099236641221374,
|
212 |
"200": 0.7786259541984732,
|
213 |
"50": 0.4618320610687023
|
214 |
},
|
215 |
+
"Reason": 0.38461538461538464,
|
216 |
+
"QA": 0.6982758620689655,
|
217 |
+
"VQA": 0.5348837209302325,
|
218 |
+
"VQA_Reasoning": 0.55
|
219 |
},
|
220 |
+
"mc-base-qwen2_vl_7b-v2-ckpt2400-2502": {
|
221 |
+
"Gui_Grounding": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
222 |
"100": 0.92,
|
223 |
"20": 0.79,
|
224 |
"200": 0.99,
|
225 |
"50": 0.88
|
226 |
},
|
227 |
+
"Embodied_Grounding": {
|
228 |
"100": 0.6068702290076335,
|
229 |
"20": 0.2099236641221374,
|
230 |
"200": 0.7824427480916031,
|
231 |
"50": 0.41603053435114506
|
232 |
},
|
233 |
+
"QA": 0.7068965517241379,
|
234 |
+
"VQA": 0.7674418604651163,
|
235 |
+
"VQA_Reasoning": 0.55,
|
236 |
+
"Reason": 0.46153846153846156
|
237 |
},
|
238 |
+
"mc-base-qwen2_vl_7b-v2-ckpt3200-2502": {
|
239 |
+
"Gui_Grounding": {
|
240 |
"100": 0.93,
|
241 |
"20": 0.84,
|
242 |
"200": 0.99,
|
243 |
"50": 0.9
|
244 |
},
|
245 |
+
"Embodied_Grounding": {
|
246 |
"100": 0.6259541984732825,
|
247 |
"20": 0.24427480916030533,
|
248 |
"200": 0.7748091603053435,
|
249 |
"50": 0.46946564885496184
|
250 |
},
|
251 |
+
"QA": 0.6810344827586207,
|
252 |
+
"VQA": 0.6976744186046512,
|
253 |
+
"VQA_Reasoning": 0.55,
|
254 |
+
"Reason": 0.38461538461538464
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
255 |
},
|
256 |
+
"mc-base-qwen2_vl_2b-v2-ckpt1600-2502": {
|
257 |
+
"Gui_Grounding": {
|
258 |
"100": 0.54,
|
259 |
"20": 0.32,
|
260 |
"200": 0.93,
|
261 |
"50": 0.38
|
262 |
},
|
263 |
+
"Embodied_Grounding": {
|
264 |
"100": 0.5038167938931297,
|
265 |
"20": 0.08015267175572519,
|
266 |
"200": 0.7175572519083969,
|
267 |
"50": 0.2748091603053435
|
268 |
},
|
269 |
+
"QA": 0.3103448275862069,
|
270 |
+
"VQA": 0.5116279069767442,
|
271 |
+
"VQA_Reasoning": 0.4,
|
272 |
+
"Reason": 0.38461538461538464
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
273 |
},
|
274 |
+
"mc-base-qwen2_vl_2b-v2-ckpt4000-2502": {
|
275 |
+
"Gui_Grounding": {
|
276 |
"100": 0.59,
|
277 |
"20": 0.39,
|
278 |
"200": 0.94,
|
279 |
"50": 0.45
|
280 |
},
|
281 |
+
"Embodied_Grounding": {
|
282 |
"100": 0.5305343511450382,
|
283 |
"20": 0.16793893129770993,
|
284 |
"200": 0.7557251908396947,
|
285 |
"50": 0.3473282442748092
|
286 |
}
|
287 |
},
|
288 |
+
"mc-base-llava_next_vicuna_13b-ckpt4000-2502": {
|
289 |
+
"Gui_Grounding": {
|
290 |
"100": 0.74,
|
291 |
"20": 0.6,
|
292 |
"200": 0.99,
|
293 |
"50": 0.68
|
294 |
},
|
295 |
+
"Embodied_Grounding": {
|
296 |
"100": 0.6259541984732825,
|
297 |
"20": 0.15267175572519084,
|
298 |
"200": 0.7748091603053435,
|
299 |
"50": 0.4122137404580153
|
300 |
},
|
301 |
+
"QA": 0.603448275862069,
|
302 |
+
"VQA": 0.4883720930232558,
|
303 |
+
"VQA_Reasoning": 0.4,
|
304 |
+
"Reason": 0.46153846153846156
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
305 |
},
|
306 |
+
"mc-reason-qwen2_vl_7b-ckpt2400-2502": {
|
307 |
+
"Gui_Grounding": {
|
308 |
"100": 0.0,
|
309 |
"20": 0.0,
|
310 |
"200": 0.0,
|
311 |
"50": 0.0
|
312 |
},
|
313 |
+
"Embodied_Grounding": {
|
314 |
"100": 0.0,
|
315 |
"20": 0.0,
|
316 |
"200": 0.003816793893129771,
|
317 |
"50": 0.0
|
318 |
},
|
319 |
+
"QA": 0.6551724137931034,
|
320 |
+
"VQA": 0.6046511627906976,
|
321 |
+
"VQA_Reasoning": 0.325,
|
322 |
+
"Reason": 0.5229885057471264
|
323 |
}
|
324 |
}
|