summary.json 12 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608
  1. {
  2. "count": 20,
  3. "platforms": "xhs,gzh,zhihu",
  4. "eval_model": "google/gemini-3.1-flash-lite",
  5. "form_b_gen_cost": 0.0006,
  6. "per_query": [
  7. {
  8. "idx": 178,
  9. "q": "风格化 工作流 工具",
  10. "forms": {
  11. "A": {
  12. "form": "A",
  13. "total": 30,
  14. "report": 26,
  15. "discard": 4,
  16. "failed": 0,
  17. "cost": 0.1087
  18. },
  19. "B": {
  20. "form": "B",
  21. "total": 30,
  22. "report": 17,
  23. "discard": 13,
  24. "failed": 0,
  25. "cost": 0.104
  26. },
  27. "C": {
  28. "form": "C",
  29. "total": 30,
  30. "report": 26,
  31. "discard": 4,
  32. "failed": 0,
  33. "cost": 0.1061
  34. }
  35. }
  36. },
  37. {
  38. "idx": 179,
  39. "q": "抠取 批处理 工具",
  40. "forms": {
  41. "A": {
  42. "form": "A",
  43. "total": 30,
  44. "report": 30,
  45. "discard": 0,
  46. "failed": 0,
  47. "cost": 0.1065
  48. },
  49. "B": {
  50. "form": "B",
  51. "total": 30,
  52. "report": 30,
  53. "discard": 0,
  54. "failed": 0,
  55. "cost": 0.1021
  56. },
  57. "C": {
  58. "form": "C",
  59. "total": 30,
  60. "report": 12,
  61. "discard": 18,
  62. "failed": 0,
  63. "cost": 0.0971
  64. }
  65. }
  66. },
  67. {
  68. "idx": 180,
  69. "q": "抽帧 批处理 工具",
  70. "forms": {
  71. "A": {
  72. "form": "A",
  73. "total": 30,
  74. "report": 30,
  75. "discard": 0,
  76. "failed": 0,
  77. "cost": 0.0918
  78. },
  79. "B": {
  80. "form": "B",
  81. "total": 30,
  82. "report": 28,
  83. "discard": 2,
  84. "failed": 0,
  85. "cost": 0.0872
  86. },
  87. "C": {
  88. "form": "C",
  89. "total": 30,
  90. "report": 27,
  91. "discard": 3,
  92. "failed": 0,
  93. "cost": 0.0908
  94. }
  95. }
  96. },
  97. {
  98. "idx": 181,
  99. "q": "识别 批处理 工具",
  100. "forms": {
  101. "A": {
  102. "form": "A",
  103. "total": 30,
  104. "report": 11,
  105. "discard": 19,
  106. "failed": 0,
  107. "cost": 0.0927
  108. },
  109. "B": {
  110. "form": "B",
  111. "total": 30,
  112. "report": 9,
  113. "discard": 21,
  114. "failed": 0,
  115. "cost": 0.0957
  116. },
  117. "C": {
  118. "form": "C",
  119. "total": 30,
  120. "report": 1,
  121. "discard": 29,
  122. "failed": 0,
  123. "cost": 0.1031
  124. }
  125. }
  126. },
  127. {
  128. "idx": 182,
  129. "q": "转换 批处理 工具",
  130. "forms": {
  131. "A": {
  132. "form": "A",
  133. "total": 30,
  134. "report": 12,
  135. "discard": 18,
  136. "failed": 0,
  137. "cost": 0.0919
  138. },
  139. "B": {
  140. "form": "B",
  141. "total": 30,
  142. "report": 11,
  143. "discard": 19,
  144. "failed": 0,
  145. "cost": 0.0836
  146. },
  147. "C": {
  148. "form": "C",
  149. "total": 0,
  150. "report": 0,
  151. "discard": 0,
  152. "failed": 0,
  153. "cost": 0.0
  154. }
  155. }
  156. },
  157. {
  158. "idx": 183,
  159. "q": "增强 批处理 工具",
  160. "forms": {
  161. "A": {
  162. "form": "A",
  163. "total": 0,
  164. "report": 0,
  165. "discard": 0,
  166. "failed": 0,
  167. "cost": 0.0
  168. },
  169. "B": {
  170. "form": "B",
  171. "total": 0,
  172. "report": 0,
  173. "discard": 0,
  174. "failed": 0,
  175. "cost": 0.0
  176. },
  177. "C": {
  178. "form": "C",
  179. "total": 0,
  180. "report": 0,
  181. "discard": 0,
  182. "failed": 0,
  183. "cost": 0.0
  184. }
  185. }
  186. },
  187. {
  188. "idx": 184,
  189. "q": "上传 数字人 工具",
  190. "forms": {
  191. "A": {
  192. "form": "A",
  193. "total": 0,
  194. "report": 0,
  195. "discard": 0,
  196. "failed": 0,
  197. "cost": 0.0
  198. },
  199. "B": {
  200. "form": "B",
  201. "total": 0,
  202. "report": 0,
  203. "discard": 0,
  204. "failed": 0,
  205. "cost": 0.0
  206. },
  207. "C": {
  208. "form": "C",
  209. "total": 0,
  210. "report": 0,
  211. "discard": 0,
  212. "failed": 0,
  213. "cost": 0.0
  214. }
  215. }
  216. },
  217. {
  218. "idx": 185,
  219. "q": "键入 数字人 工具",
  220. "forms": {
  221. "A": {
  222. "form": "A",
  223. "total": 0,
  224. "report": 0,
  225. "discard": 0,
  226. "failed": 0,
  227. "cost": 0.0
  228. },
  229. "B": {
  230. "form": "B",
  231. "total": 0,
  232. "report": 0,
  233. "discard": 0,
  234. "failed": 0,
  235. "cost": 0.0
  236. },
  237. "C": {
  238. "form": "C",
  239. "total": 0,
  240. "report": 0,
  241. "discard": 0,
  242. "failed": 0,
  243. "cost": 0.0
  244. }
  245. }
  246. },
  247. {
  248. "idx": 186,
  249. "q": "元素生成 数字人 工具",
  250. "forms": {
  251. "A": {
  252. "form": "A",
  253. "total": 0,
  254. "report": 0,
  255. "discard": 0,
  256. "failed": 0,
  257. "cost": 0.0
  258. },
  259. "B": {
  260. "form": "B",
  261. "total": 0,
  262. "report": 0,
  263. "discard": 0,
  264. "failed": 0,
  265. "cost": 0.0
  266. },
  267. "C": {
  268. "form": "C",
  269. "total": 0,
  270. "report": 0,
  271. "discard": 0,
  272. "failed": 0,
  273. "cost": 0.0
  274. }
  275. }
  276. },
  277. {
  278. "idx": 187,
  279. "q": "结构生成 版式 工具",
  280. "forms": {
  281. "A": {
  282. "form": "A",
  283. "total": 0,
  284. "report": 0,
  285. "discard": 0,
  286. "failed": 0,
  287. "cost": 0.0
  288. },
  289. "B": {
  290. "form": "B",
  291. "total": 0,
  292. "report": 0,
  293. "discard": 0,
  294. "failed": 0,
  295. "cost": 0.0
  296. },
  297. "C": {
  298. "form": "C",
  299. "total": 0,
  300. "report": 0,
  301. "discard": 0,
  302. "failed": 0,
  303. "cost": 0.0
  304. }
  305. }
  306. },
  307. {
  308. "idx": 188,
  309. "q": "键入 模板 工具",
  310. "forms": {
  311. "A": {
  312. "form": "A",
  313. "total": 0,
  314. "report": 0,
  315. "discard": 0,
  316. "failed": 0,
  317. "cost": 0.0
  318. },
  319. "B": {
  320. "form": "B",
  321. "total": 0,
  322. "report": 0,
  323. "discard": 0,
  324. "failed": 0,
  325. "cost": 0.0
  326. },
  327. "C": {
  328. "form": "C",
  329. "total": 30,
  330. "report": 1,
  331. "discard": 29,
  332. "failed": 0,
  333. "cost": 0.0931
  334. }
  335. }
  336. },
  337. {
  338. "idx": 189,
  339. "q": "结构生成 模板 工具",
  340. "forms": {
  341. "A": {
  342. "form": "A",
  343. "total": 30,
  344. "report": 19,
  345. "discard": 11,
  346. "failed": 0,
  347. "cost": 0.1079
  348. },
  349. "B": {
  350. "form": "B",
  351. "total": 30,
  352. "report": 17,
  353. "discard": 13,
  354. "failed": 0,
  355. "cost": 0.1072
  356. },
  357. "C": {
  358. "form": "C",
  359. "total": 30,
  360. "report": 14,
  361. "discard": 16,
  362. "failed": 0,
  363. "cost": 0.0939
  364. }
  365. }
  366. },
  367. {
  368. "idx": 190,
  369. "q": "替换 模板 工具",
  370. "forms": {
  371. "A": {
  372. "form": "A",
  373. "total": 30,
  374. "report": 11,
  375. "discard": 19,
  376. "failed": 0,
  377. "cost": 0.0954
  378. },
  379. "B": {
  380. "form": "B",
  381. "total": 30,
  382. "report": 2,
  383. "discard": 28,
  384. "failed": 0,
  385. "cost": 0.0892
  386. },
  387. "C": {
  388. "form": "C",
  389. "total": 30,
  390. "report": 5,
  391. "discard": 25,
  392. "failed": 0,
  393. "cost": 0.0797
  394. }
  395. }
  396. },
  397. {
  398. "idx": 191,
  399. "q": "上传 参考图 工具",
  400. "forms": {
  401. "A": {
  402. "form": "A",
  403. "total": 30,
  404. "report": 30,
  405. "discard": 0,
  406. "failed": 0,
  407. "cost": 0.1074
  408. },
  409. "B": {
  410. "form": "B",
  411. "total": 30,
  412. "report": 22,
  413. "discard": 8,
  414. "failed": 0,
  415. "cost": 0.1081
  416. },
  417. "C": {
  418. "form": "C",
  419. "total": 30,
  420. "report": 29,
  421. "discard": 1,
  422. "failed": 0,
  423. "cost": 0.1144
  424. }
  425. }
  426. },
  427. {
  428. "idx": 192,
  429. "q": "识别 参考图 工具",
  430. "forms": {
  431. "A": {
  432. "form": "A",
  433. "total": 30,
  434. "report": 21,
  435. "discard": 9,
  436. "failed": 0,
  437. "cost": 0.0964
  438. },
  439. "B": {
  440. "form": "B",
  441. "total": 30,
  442. "report": 13,
  443. "discard": 17,
  444. "failed": 0,
  445. "cost": 0.1046
  446. },
  447. "C": {
  448. "form": "C",
  449. "total": 30,
  450. "report": 9,
  451. "discard": 21,
  452. "failed": 0,
  453. "cost": 0.0856
  454. }
  455. }
  456. },
  457. {
  458. "idx": 193,
  459. "q": "反推 参考图 工具",
  460. "forms": {
  461. "A": {
  462. "form": "A",
  463. "total": 30,
  464. "report": 30,
  465. "discard": 0,
  466. "failed": 0,
  467. "cost": 0.1116
  468. },
  469. "B": {
  470. "form": "B",
  471. "total": 30,
  472. "report": 30,
  473. "discard": 0,
  474. "failed": 0,
  475. "cost": 0.1122
  476. },
  477. "C": {
  478. "form": "C",
  479. "total": 30,
  480. "report": 29,
  481. "discard": 1,
  482. "failed": 0,
  483. "cost": 0.1102
  484. }
  485. }
  486. },
  487. {
  488. "idx": 194,
  489. "q": "风格化 参考图 工具",
  490. "forms": {
  491. "A": {
  492. "form": "A",
  493. "total": 30,
  494. "report": 30,
  495. "discard": 0,
  496. "failed": 0,
  497. "cost": 0.1068
  498. },
  499. "B": {
  500. "form": "B",
  501. "total": 30,
  502. "report": 30,
  503. "discard": 0,
  504. "failed": 0,
  505. "cost": 0.1099
  506. },
  507. "C": {
  508. "form": "C",
  509. "total": 30,
  510. "report": 29,
  511. "discard": 1,
  512. "failed": 0,
  513. "cost": 0.1091
  514. }
  515. }
  516. },
  517. {
  518. "idx": 195,
  519. "q": "调整 参考图 工具",
  520. "forms": {
  521. "A": {
  522. "form": "A",
  523. "total": 30,
  524. "report": 29,
  525. "discard": 1,
  526. "failed": 0,
  527. "cost": 0.1136
  528. },
  529. "B": {
  530. "form": "B",
  531. "total": 30,
  532. "report": 27,
  533. "discard": 3,
  534. "failed": 0,
  535. "cost": 0.1187
  536. },
  537. "C": {
  538. "form": "C",
  539. "total": 30,
  540. "report": 25,
  541. "discard": 5,
  542. "failed": 0,
  543. "cost": 0.1136
  544. }
  545. }
  546. },
  547. {
  548. "idx": 196,
  549. "q": "上传 参考视频 工具",
  550. "forms": {
  551. "A": {
  552. "form": "A",
  553. "total": 30,
  554. "report": 27,
  555. "discard": 3,
  556. "failed": 0,
  557. "cost": 0.1067
  558. },
  559. "B": {
  560. "form": "B",
  561. "total": 20,
  562. "report": 14,
  563. "discard": 6,
  564. "failed": 0,
  565. "cost": 0.0587
  566. },
  567. "C": {
  568. "form": "C",
  569. "total": 20,
  570. "report": 10,
  571. "discard": 10,
  572. "failed": 0,
  573. "cost": 0.0539
  574. }
  575. }
  576. },
  577. {
  578. "idx": 197,
  579. "q": "抽帧 参考视频 工具",
  580. "forms": {
  581. "A": {
  582. "form": "A",
  583. "total": 30,
  584. "report": 29,
  585. "discard": 1,
  586. "failed": 0,
  587. "cost": 0.096
  588. },
  589. "B": {
  590. "form": "B",
  591. "total": 30,
  592. "report": 26,
  593. "discard": 4,
  594. "failed": 0,
  595. "cost": 0.0887
  596. },
  597. "C": {
  598. "form": "C",
  599. "total": 30,
  600. "report": 30,
  601. "discard": 0,
  602. "failed": 0,
  603. "cost": 0.0929
  604. }
  605. }
  606. }
  607. ]
  608. }