kristaller486 commited on
Commit
b91759b
·
verified ·
1 Parent(s): 5d0b7a9

add gpt-4.1 series

Browse files
Files changed (1) hide show
  1. index.html +148 -40
index.html CHANGED
@@ -118,7 +118,7 @@
118
 
119
 
120
 
121
- <div class="progress-fill" style="width: 91.43518518518519%"></div>
122
  </div>
123
  <span class="score-value">
124
 
@@ -154,7 +154,7 @@
154
 
155
 
156
 
157
- <div class="progress-fill" style="width: 91.2037037037037%"></div>
158
  </div>
159
  <span class="score-value">
160
 
@@ -190,7 +190,7 @@
190
 
191
 
192
 
193
- <div class="progress-fill" style="width: 89.81481481481481%"></div>
194
  </div>
195
  <span class="score-value">
196
 
@@ -226,7 +226,7 @@
226
 
227
 
228
 
229
- <div class="progress-fill" style="width: 88.88888888888889%"></div>
230
  </div>
231
  <span class="score-value">
232
 
@@ -262,7 +262,7 @@
262
 
263
 
264
 
265
- <div class="progress-fill" style="width: 88.19444444444444%"></div>
266
  </div>
267
  <span class="score-value">
268
 
@@ -298,7 +298,7 @@
298
 
299
 
300
 
301
- <div class="progress-fill" style="width: 87.73148148148148%"></div>
302
  </div>
303
  <span class="score-value">
304
 
@@ -334,7 +334,7 @@
334
 
335
 
336
 
337
- <div class="progress-fill" style="width: 86.3425925925926%"></div>
338
  </div>
339
  <span class="score-value">
340
 
@@ -370,7 +370,7 @@
370
 
371
 
372
 
373
- <div class="progress-fill" style="width: 86.11111111111111%"></div>
374
  </div>
375
  <span class="score-value">
376
 
@@ -406,7 +406,7 @@
406
 
407
 
408
 
409
- <div class="progress-fill" style="width: 84.02777777777779%"></div>
410
  </div>
411
  <span class="score-value">
412
 
@@ -442,7 +442,7 @@
442
 
443
 
444
 
445
- <div class="progress-fill" style="width: 83.7962962962963%"></div>
446
  </div>
447
  <span class="score-value">
448
 
@@ -478,7 +478,7 @@
478
 
479
 
480
 
481
- <div class="progress-fill" style="width: 83.56481481481481%"></div>
482
  </div>
483
  <span class="score-value">
484
 
@@ -514,7 +514,7 @@
514
 
515
 
516
 
517
- <div class="progress-fill" style="width: 81.94444444444444%"></div>
518
  </div>
519
  <span class="score-value">
520
 
@@ -550,7 +550,7 @@
550
 
551
 
552
 
553
- <div class="progress-fill" style="width: 80.55555555555556%"></div>
554
  </div>
555
  <span class="score-value">
556
 
@@ -586,7 +586,7 @@
586
 
587
 
588
 
589
- <div class="progress-fill" style="width: 79.39814814814815%"></div>
590
  </div>
591
  <span class="score-value">
592
 
@@ -622,7 +622,7 @@
622
 
623
 
624
 
625
- <div class="progress-fill" style="width: 77.08333333333334%"></div>
626
  </div>
627
  <span class="score-value">
628
 
@@ -658,7 +658,7 @@
658
 
659
 
660
 
661
- <div class="progress-fill" style="width: 75.92592592592592%"></div>
662
  </div>
663
  <span class="score-value">
664
 
@@ -694,7 +694,7 @@
694
 
695
 
696
 
697
- <div class="progress-fill" style="width: 74.53703703703704%"></div>
698
  </div>
699
  <span class="score-value">
700
 
@@ -730,7 +730,7 @@
730
 
731
 
732
 
733
- <div class="progress-fill" style="width: 74.30555555555556%"></div>
734
  </div>
735
  <span class="score-value">
736
 
@@ -766,7 +766,7 @@
766
 
767
 
768
 
769
- <div class="progress-fill" style="width: 71.75925925925925%"></div>
770
  </div>
771
  <span class="score-value">
772
 
@@ -802,7 +802,7 @@
802
 
803
 
804
 
805
- <div class="progress-fill" style="width: 71.75925925925925%"></div>
806
  </div>
807
  <span class="score-value">
808
 
@@ -838,7 +838,7 @@
838
 
839
 
840
 
841
- <div class="progress-fill" style="width: 71.06481481481481%"></div>
842
  </div>
843
  <span class="score-value">
844
 
@@ -874,7 +874,7 @@
874
 
875
 
876
 
877
- <div class="progress-fill" style="width: 70.60185185185186%"></div>
878
  </div>
879
  <span class="score-value">
880
 
@@ -910,7 +910,7 @@
910
 
911
 
912
 
913
- <div class="progress-fill" style="width: 70.60185185185186%"></div>
914
  </div>
915
  <span class="score-value">
916
 
@@ -946,7 +946,7 @@
946
 
947
 
948
 
949
- <div class="progress-fill" style="width: 66.89814814814815%"></div>
950
  </div>
951
  <span class="score-value">
952
 
@@ -982,7 +982,7 @@
982
 
983
 
984
 
985
- <div class="progress-fill" style="width: 64.12037037037037%"></div>
986
  </div>
987
  <span class="score-value">
988
 
@@ -1018,7 +1018,7 @@
1018
 
1019
 
1020
 
1021
- <div class="progress-fill" style="width: 61.57407407407408%"></div>
1022
  </div>
1023
  <span class="score-value">
1024
 
@@ -1054,7 +1054,7 @@
1054
 
1055
 
1056
 
1057
- <div class="progress-fill" style="width: 59.95370370370371%"></div>
1058
  </div>
1059
  <span class="score-value">
1060
 
@@ -1090,7 +1090,7 @@
1090
 
1091
 
1092
 
1093
- <div class="progress-fill" style="width: 58.796296296296305%"></div>
1094
  </div>
1095
  <span class="score-value">
1096
 
@@ -1126,7 +1126,7 @@
1126
 
1127
 
1128
 
1129
- <div class="progress-fill" style="width: 57.407407407407405%"></div>
1130
  </div>
1131
  <span class="score-value">
1132
 
@@ -1162,7 +1162,7 @@
1162
 
1163
 
1164
 
1165
- <div class="progress-fill" style="width: 51.85185185185186%"></div>
1166
  </div>
1167
  <span class="score-value">
1168
 
@@ -1198,7 +1198,7 @@
1198
 
1199
 
1200
 
1201
- <div class="progress-fill" style="width: 51.620370370370374%"></div>
1202
  </div>
1203
  <span class="score-value">
1204
 
@@ -1234,7 +1234,7 @@
1234
 
1235
 
1236
 
1237
- <div class="progress-fill" style="width: 49.768518518518526%"></div>
1238
  </div>
1239
  <span class="score-value">
1240
 
@@ -1270,7 +1270,7 @@
1270
 
1271
 
1272
 
1273
- <div class="progress-fill" style="width: 46.99074074074075%"></div>
1274
  </div>
1275
  <span class="score-value">
1276
 
@@ -1282,8 +1282,44 @@
1282
  <td class="num mono" data-label="Всего токенов">183,215</td>
1283
  </tr>
1284
 
1285
- <tr data-model="openrouter/mistralai/mistral-nemo">
1286
  <td class="rank mono sticky-0" data-label="#">#34</td>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1287
  <td class="model-name sticky-1" data-label="Модель">Mistral-Nemo (Mistral API)</td>
1288
  <td class="num mono" data-label="Критичные/1000">
1289
 
@@ -1306,7 +1342,7 @@
1306
 
1307
 
1308
 
1309
- <div class="progress-fill" style="width: 35.879629629629626%"></div>
1310
  </div>
1311
  <span class="score-value">
1312
 
@@ -1318,8 +1354,44 @@
1318
  <td class="num mono" data-label="Всего токенов">53,243</td>
1319
  </tr>
1320
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1321
  <tr data-model="openrouter/minimax/minimax-m2:free">
1322
- <td class="rank mono sticky-0" data-label="#">#35</td>
1323
  <td class="model-name sticky-1" data-label="Модель">MiniMaxAI/MiniMax-M2 (Minimax API)</td>
1324
  <td class="num mono" data-label="Критичные/1000">
1325
 
@@ -1342,7 +1414,7 @@
1342
 
1343
 
1344
 
1345
- <div class="progress-fill" style="width: 30.09259259259259%"></div>
1346
  </div>
1347
  <span class="score-value">
1348
 
@@ -1355,7 +1427,7 @@
1355
  </tr>
1356
 
1357
  <tr data-model="openrouter/minimax/minimax-m2:free">
1358
- <td class="rank mono sticky-0" data-label="#">#36</td>
1359
  <td class="model-name sticky-1" data-label="Модель">MiniMaxAI/MiniMax-M2 (Minimax API, recommend params)</td>
1360
  <td class="num mono" data-label="Критичные/1000">
1361
 
@@ -1378,7 +1450,7 @@
1378
 
1379
 
1380
 
1381
- <div class="progress-fill" style="width: 0.0%"></div>
1382
  </div>
1383
  <span class="score-value">
1384
 
@@ -1390,6 +1462,42 @@
1390
  <td class="num mono" data-label="Всего токенов">203,067</td>
1391
  </tr>
1392
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1393
  </tbody>
1394
  </table>
1395
  </div>
@@ -1413,7 +1521,7 @@
1413
  </div>
1414
  <p class="info-text">Если хотите, чтобы я добавил ту или иную модель в лидерборд - не стесняйтесь открыть issue/pull request на Github.</p>
1415
  <p class="info-text">
1416
- Обновлено: 2025-11-19 15:42:11 | Всего моделей: 36 | <a href="https://github.com/kristaller486/RuQualBench">GitHub</a> | <a href="https://t.me/krists">Telegram</a>
1417
  </p>
1418
  </div>
1419
  <script>
 
118
 
119
 
120
 
121
+ <div class="progress-fill" style="width: 93.80234505862647%"></div>
122
  </div>
123
  <span class="score-value">
124
 
 
154
 
155
 
156
 
157
+ <div class="progress-fill" style="width: 93.63484087102178%"></div>
158
  </div>
159
  <span class="score-value">
160
 
 
190
 
191
 
192
 
193
+ <div class="progress-fill" style="width: 92.62981574539364%"></div>
194
  </div>
195
  <span class="score-value">
196
 
 
226
 
227
 
228
 
229
+ <div class="progress-fill" style="width: 91.95979899497488%"></div>
230
  </div>
231
  <span class="score-value">
232
 
 
262
 
263
 
264
 
265
+ <div class="progress-fill" style="width: 91.4572864321608%"></div>
266
  </div>
267
  <span class="score-value">
268
 
 
298
 
299
 
300
 
301
+ <div class="progress-fill" style="width: 91.12227805695142%"></div>
302
  </div>
303
  <span class="score-value">
304
 
 
334
 
335
 
336
 
337
+ <div class="progress-fill" style="width: 90.11725293132329%"></div>
338
  </div>
339
  <span class="score-value">
340
 
 
370
 
371
 
372
 
373
+ <div class="progress-fill" style="width: 89.9497487437186%"></div>
374
  </div>
375
  <span class="score-value">
376
 
 
406
 
407
 
408
 
409
+ <div class="progress-fill" style="width: 88.44221105527639%"></div>
410
  </div>
411
  <span class="score-value">
412
 
 
442
 
443
 
444
 
445
+ <div class="progress-fill" style="width: 88.2747068676717%"></div>
446
  </div>
447
  <span class="score-value">
448
 
 
478
 
479
 
480
 
481
+ <div class="progress-fill" style="width: 88.107202680067%"></div>
482
  </div>
483
  <span class="score-value">
484
 
 
514
 
515
 
516
 
517
+ <div class="progress-fill" style="width: 86.93467336683418%"></div>
518
  </div>
519
  <span class="score-value">
520
 
 
550
 
551
 
552
 
553
+ <div class="progress-fill" style="width: 85.92964824120604%"></div>
554
  </div>
555
  <span class="score-value">
556
 
 
586
 
587
 
588
 
589
+ <div class="progress-fill" style="width: 85.09212730318258%"></div>
590
  </div>
591
  <span class="score-value">
592
 
 
622
 
623
 
624
 
625
+ <div class="progress-fill" style="width: 83.41708542713569%"></div>
626
  </div>
627
  <span class="score-value">
628
 
 
658
 
659
 
660
 
661
+ <div class="progress-fill" style="width: 82.57956448911223%"></div>
662
  </div>
663
  <span class="score-value">
664
 
 
694
 
695
 
696
 
697
+ <div class="progress-fill" style="width: 81.57453936348409%"></div>
698
  </div>
699
  <span class="score-value">
700
 
 
730
 
731
 
732
 
733
+ <div class="progress-fill" style="width: 81.4070351758794%"></div>
734
  </div>
735
  <span class="score-value">
736
 
 
766
 
767
 
768
 
769
+ <div class="progress-fill" style="width: 79.5644891122278%"></div>
770
  </div>
771
  <span class="score-value">
772
 
 
802
 
803
 
804
 
805
+ <div class="progress-fill" style="width: 79.5644891122278%"></div>
806
  </div>
807
  <span class="score-value">
808
 
 
838
 
839
 
840
 
841
+ <div class="progress-fill" style="width: 79.06197654941374%"></div>
842
  </div>
843
  <span class="score-value">
844
 
 
874
 
875
 
876
 
877
+ <div class="progress-fill" style="width: 78.72696817420434%"></div>
878
  </div>
879
  <span class="score-value">
880
 
 
910
 
911
 
912
 
913
+ <div class="progress-fill" style="width: 78.72696817420434%"></div>
914
  </div>
915
  <span class="score-value">
916
 
 
946
 
947
 
948
 
949
+ <div class="progress-fill" style="width: 76.04690117252932%"></div>
950
  </div>
951
  <span class="score-value">
952
 
 
982
 
983
 
984
 
985
+ <div class="progress-fill" style="width: 74.03685092127303%"></div>
986
  </div>
987
  <span class="score-value">
988
 
 
1018
 
1019
 
1020
 
1021
+ <div class="progress-fill" style="width: 72.19430485762143%"></div>
1022
  </div>
1023
  <span class="score-value">
1024
 
 
1054
 
1055
 
1056
 
1057
+ <div class="progress-fill" style="width: 71.0217755443886%"></div>
1058
  </div>
1059
  <span class="score-value">
1060
 
 
1090
 
1091
 
1092
 
1093
+ <div class="progress-fill" style="width: 70.18425460636516%"></div>
1094
  </div>
1095
  <span class="score-value">
1096
 
 
1126
 
1127
 
1128
 
1129
+ <div class="progress-fill" style="width: 69.17922948073702%"></div>
1130
  </div>
1131
  <span class="score-value">
1132
 
 
1162
 
1163
 
1164
 
1165
+ <div class="progress-fill" style="width: 65.15912897822444%"></div>
1166
  </div>
1167
  <span class="score-value">
1168
 
 
1198
 
1199
 
1200
 
1201
+ <div class="progress-fill" style="width: 64.99162479061977%"></div>
1202
  </div>
1203
  <span class="score-value">
1204
 
 
1234
 
1235
 
1236
 
1237
+ <div class="progress-fill" style="width: 63.65159128978224%"></div>
1238
  </div>
1239
  <span class="score-value">
1240
 
 
1270
 
1271
 
1272
 
1273
+ <div class="progress-fill" style="width: 61.64154103852596%"></div>
1274
  </div>
1275
  <span class="score-value">
1276
 
 
1282
  <td class="num mono" data-label="Всего токенов">183,215</td>
1283
  </tr>
1284
 
1285
+ <tr data-model="openai/gpt-4.1">
1286
  <td class="rank mono sticky-0" data-label="#">#34</td>
1287
+ <td class="model-name sticky-1" data-label="Модель">GPT-4.1</td>
1288
+ <td class="num mono" data-label="Критичные/1000">
1289
+
1290
+ 0.35 ± 0.01
1291
+
1292
+ </td>
1293
+ <td class="num mono" data-label="Обычные/1000">
1294
+
1295
+ 1.36 ± 0.06
1296
+
1297
+ </td>
1298
+ <td class="num mono" data-label="Доп./1000">
1299
+
1300
+ 0.65 ± 0.03
1301
+
1302
+ </td>
1303
+ <td data-label="Нормировано ошибок">
1304
+ <div class="score-cell">
1305
+ <div class="progress-bar">
1306
+
1307
+
1308
+
1309
+ <div class="progress-fill" style="width: 59.96649916247906%"></div>
1310
+ </div>
1311
+ <span class="score-value">
1312
+
1313
+ 2.39 ± 0.04
1314
+
1315
+ </span>
1316
+ </div>
1317
+ </td>
1318
+ <td class="num mono" data-label="Всего токенов">85,822</td>
1319
+ </tr>
1320
+
1321
+ <tr data-model="openrouter/mistralai/mistral-nemo">
1322
+ <td class="rank mono sticky-0" data-label="#">#35</td>
1323
  <td class="model-name sticky-1" data-label="Модель">Mistral-Nemo (Mistral API)</td>
1324
  <td class="num mono" data-label="Критичные/1000">
1325
 
 
1342
 
1343
 
1344
 
1345
+ <div class="progress-fill" style="width: 53.60134003350083%"></div>
1346
  </div>
1347
  <span class="score-value">
1348
 
 
1354
  <td class="num mono" data-label="Всего токенов">53,243</td>
1355
  </tr>
1356
 
1357
+ <tr data-model="openai/gpt-4.1-mini">
1358
+ <td class="rank mono sticky-0" data-label="#">#36</td>
1359
+ <td class="model-name sticky-1" data-label="Модель">GPT-4.1-mini</td>
1360
+ <td class="num mono" data-label="Критичные/1000">
1361
+
1362
+ 0.30 ± 0.02
1363
+
1364
+ </td>
1365
+ <td class="num mono" data-label="Обычные/1000">
1366
+
1367
+ 2.13 ± 0.19
1368
+
1369
+ </td>
1370
+ <td class="num mono" data-label="Доп./1000">
1371
+
1372
+ 0.54 ± 0.05
1373
+
1374
+ </td>
1375
+ <td data-label="Нормировано ошибок">
1376
+ <div class="score-cell">
1377
+ <div class="progress-bar">
1378
+
1379
+
1380
+
1381
+ <div class="progress-fill" style="width: 49.748743718592955%"></div>
1382
+ </div>
1383
+ <span class="score-value">
1384
+
1385
+ 3.00 ± 0.20
1386
+
1387
+ </span>
1388
+ </div>
1389
+ </td>
1390
+ <td class="num mono" data-label="Всего токенов">66,098</td>
1391
+ </tr>
1392
+
1393
  <tr data-model="openrouter/minimax/minimax-m2:free">
1394
+ <td class="rank mono sticky-0" data-label="#">#37</td>
1395
  <td class="model-name sticky-1" data-label="Модель">MiniMaxAI/MiniMax-M2 (Minimax API)</td>
1396
  <td class="num mono" data-label="Критичные/1000">
1397
 
 
1414
 
1415
 
1416
 
1417
+ <div class="progress-fill" style="width: 49.41373534338358%"></div>
1418
  </div>
1419
  <span class="score-value">
1420
 
 
1427
  </tr>
1428
 
1429
  <tr data-model="openrouter/minimax/minimax-m2:free">
1430
+ <td class="rank mono sticky-0" data-label="#">#38</td>
1431
  <td class="model-name sticky-1" data-label="Модель">MiniMaxAI/MiniMax-M2 (Minimax API, recommend params)</td>
1432
  <td class="num mono" data-label="Критичные/1000">
1433
 
 
1450
 
1451
 
1452
 
1453
+ <div class="progress-fill" style="width: 27.63819095477387%"></div>
1454
  </div>
1455
  <span class="score-value">
1456
 
 
1462
  <td class="num mono" data-label="Всего токенов">203,067</td>
1463
  </tr>
1464
 
1465
+ <tr data-model="openai/gpt-4.1-nano">
1466
+ <td class="rank mono sticky-0" data-label="#">#39</td>
1467
+ <td class="model-name sticky-1" data-label="Модель">GPT-4.1-nano</td>
1468
+ <td class="num mono" data-label="Критичные/1000">
1469
+
1470
+ 0.87 ± 0.14
1471
+
1472
+ </td>
1473
+ <td class="num mono" data-label="Обычные/1000">
1474
+
1475
+ 3.74 ± 0.22
1476
+
1477
+ </td>
1478
+ <td class="num mono" data-label="Доп./1000">
1479
+
1480
+ 0.99 ± 0.02
1481
+
1482
+ </td>
1483
+ <td data-label="Нормировано ошибок">
1484
+ <div class="score-cell">
1485
+ <div class="progress-bar">
1486
+
1487
+
1488
+
1489
+ <div class="progress-fill" style="width: 0.0%"></div>
1490
+ </div>
1491
+ <span class="score-value">
1492
+
1493
+ 5.97 ± 0.32
1494
+
1495
+ </span>
1496
+ </div>
1497
+ </td>
1498
+ <td class="num mono" data-label="Всего токенов">65,110</td>
1499
+ </tr>
1500
+
1501
  </tbody>
1502
  </table>
1503
  </div>
 
1521
  </div>
1522
  <p class="info-text">Если хотите, чтобы я добавил ту или иную модель в лидерборд - не стесняйтесь открыть issue/pull request на Github.</p>
1523
  <p class="info-text">
1524
+ Обновлено: 2025-11-19 18:11:00 | Всего моделей: 39 | <a href="https://github.com/kristaller486/RuQualBench">GitHub</a> | <a href="https://t.me/krists">Telegram</a>
1525
  </p>
1526
  </div>
1527
  <script>