| Sessions | 122 |
| Train | 44 (36.1%) |
| Test | 42 (34.4%) |
| Weight | 36 |
| Duration | 01:44:47 |
| Avg | 00:00:51 |
| Errors | 8 |
| Best Score | 0.00 |
| Tokens | 1,452,745 |
| In Tokens | 1,127,382 |
| Out Tokens | 325,363 |
| Retries | 32 |
| Suite | Session | Steps | Duration | Err | Train | Test | Score | Tokens | Attempts | Retries | Model |
|---|---|---|---|---|---|---|---|---|---|---|---|
| sessions | 25.085.0643 | 2 | 00:00:28 | - | ✓ | ✓ | 0.00 | 5,740 | 2 | 0 | gemini-2.5-pro-exp-03-25 |
| sessions | 25.085.2059 | 2 | 00:00:28 | - | ✓ | ✓ | 0.00 | 7,236 | 2 | 0 | gemini-2.5-pro-exp-03-25 |
| sessions_001 | 25.054.0526 | 12 | 00:01:56 | - | ✗ | - | 8.00 | 34,613 | 12 | 0 | - |
| sessions_001 | 25.054.0536 | 2 | 00:00:08 | - | ✓ | ✓ | 0.00 | 4,250 | 2 | 0 | - |
| sessions_001 | 25.054.0546 | 4 | 00:00:22 | - | ✓ | ✓ | 0.00 | 9,610 | 4 | 0 | - |
| sessions_001 | 25.054.1212 | 2 | 00:00:09 | - | ✓ | ✓ | 0.00 | 4,361 | 2 | 0 | - |
| sessions_001 | 25.055.0614 | 8 | 00:01:33 | - | ✓ | ✓ | 0.00 | 19,650 | 8 | 0 | - |
| sessions_001 | 25.055.0629 | 12 | 00:01:31 | - | ✗ | - | 7.00 | 29,116 | 12 | 0 | - |
| sessions_001 | 25.055.0645 | 8 | 00:01:18 | - | ✓ | ✓ | 0.00 | 25,929 | 8 | 0 | - |
| sessions_001 | 25.055.1133 | 2 | 00:00:09 | - | ✓ | - | 0.00 | 4,255 | 2 | 0 | - |
| sessions_001 | 25.055.1137 | 2 | 00:00:08 | - | ✗ | - | 14.00 | 4,286 | 2 | 0 | - |
| sessions_001 | 25.055.1138 | 2 | 00:00:10 | - | ✗ | - | 14.00 | 4,338 | 2 | 0 | - |
| sessions_001 | 25.055.1140 | 2 | 00:00:06 | - | ✗ | - | 14.00 | 3,918 | 2 | 0 | - |
| sessions_001 | 25.055.1151 | 9 | 00:01:08 | - | ✗ | - | 14.00 | 20,475 | 9 | 0 | - |
| sessions_001 | 25.055.1152 | 2 | 00:00:08 | - | ✓ | ✓ | 0.00 | 4,163 | 2 | 0 | - |
| sessions_001 | 25.055.1155 | 7 | 00:00:34 | - | ✗ | - | 14.00 | 14,013 | 7 | 0 | - |
| sessions_001 | 25.055.1156 | 12 | 00:01:47 | - | ✗ | - | 14.00 | 25,257 | 12 | 0 | - |
| sessions_001 | 25.055.1202 | 12 | 00:01:54 | - | ✗ | - | 14.00 | 45,127 | 12 | 0 | - |
| sessions_001 | 25.055.1205 | 2 | 00:00:08 | - | ✓ | ✓ | 0.00 | 4,102 | 2 | 0 | - |
| sessions_001 | 25.055.1314 | 2 | 00:00:08 | - | ✓ | ✓ | 0.00 | 4,219 | 2 | 0 | - |
| sessions_001 | 25.055.1355 | 12 | 00:02:53 | - | ✗ | - | 14.00 | 62,182 | 12 | 0 | - |
| sessions_001 | 25.058.0727 | 12 | 00:01:45 | - | - | - | - | 34,726 | 12 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_001 | 25.058.0730 | 8 | 00:00:44 | - | - | - | - | 17,999 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_001 | 25.058.0735 | 2 | 00:00:07 | - | - | - | - | 4,095 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_001 | 25.058.0736 | 12 | 00:01:36 | - | - | - | - | 27,869 | 12 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_001 | 25.058.0802 | 12 | 00:01:45 | - | - | - | - | 31,505 | 12 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_001 | 25.058.0950 | 18 | 00:02:45 | - | - | - | - | 59,327 | 18 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_001 | 25.058.1132 | 14 | 00:02:22 | - | - | - | - | 47,203 | 14 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_001 | 25.061.1802 | 18 | 00:03:02 | - | - | - | - | 51,456 | 18 | 0 | - |
| sessions_001 | 25.061.2017 | 14 | 00:02:43 | - | - | - | - | 36,599 | 14 | 0 | - |
| sessions_002 | 25.078.1430 | 4 | 00:00:38 | - | ✗ | - | 7.00 | 9,738 | 4 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.078.1450 | 4 | 00:00:34 | - | ✓ | ✓ | 0.00 | 9,078 | 4 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.078.1536 | 2 | 00:00:12 | ✗ | ✗ | - | 14.00 | 3,392 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.078.1538 | 2 | 00:00:16 | ✗ | ✗ | - | 8.00 | 3,450 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.078.1545 | 2 | 00:00:12 | ✗ | ✗ | - | 12.00 | 3,340 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.078.1658 | 2 | 00:00:13 | - | ✓ | ✓ | 0.00 | 3,412 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.078.1700 | 2 | 00:00:12 | - | ✗ | - | 14.00 | 3,356 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.078.1711 | 2 | 00:00:14 | - | ✗ | - | 8.00 | 3,598 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.078.2010 | 2 | 00:00:13 | - | ✓ | ✓ | 0.00 | 3,374 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0449 | 2 | 00:00:15 | - | ✗ | - | 14.00 | 3,677 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0602 | 1 | 00:00:26 | - | - | - | - | 1,912 | 1 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0603 | 1 | 00:00:07 | - | - | - | - | 1,674 | 1 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0610 | 2 | 00:00:15 | - | - | - | - | 3,304 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0614 | 2 | 00:00:15 | - | - | - | - | 3,461 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0618 | 2 | 00:00:15 | ✗ | - | - | - | 3,369 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0620 | 2 | 00:00:13 | ✗ | - | - | - | 3,409 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0642 | 2 | 00:00:30 | ✗ | - | - | - | 3,512 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0653 | 2 | 00:00:14 | ✗ | - | - | - | 3,462 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0654 | 2 | 00:00:13 | - | ✗ | - | 14.00 | 3,285 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0704 | 2 | 00:00:22 | - | ✗ | - | 8.00 | 3,526 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0708 | 2 | 00:00:09 | - | ✗ | - | 14.00 | 3,200 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0709 | 2 | 00:00:13 | - | ✓ | ✓ | 0.00 | 3,552 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0740 | 2 | 00:00:19 | - | ✗ | - | 14.00 | 3,472 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0741 | 2 | 00:00:37 | - | ✗ | - | 14.00 | 3,660 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0743 | 2 | 00:00:24 | - | ✗ | - | 15.00 | 3,710 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0744 | 2 | 00:00:19 | - | ✗ | - | 14.00 | 3,259 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0747 | 2 | 00:00:12 | - | - | - | - | 1,727 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0749 | 2 | 00:00:19 | - | ✗ | - | 8.00 | 3,593 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0753 | 3 | 00:01:11 | - | ✗ | - | 8.00 | 5,911 | 3 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0800 | 4 | 00:01:05 | - | ✗ | - | 14.00 | 8,740 | 4 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0815 | 4 | 00:00:30 | - | ✗ | - | 14.00 | 7,849 | 4 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0818 | 4 | 00:00:31 | - | ✓ | ✓ | 0.00 | 8,835 | 4 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0825 | 4 | 00:00:45 | - | ✗ | - | 14.00 | 8,376 | 4 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0855 | 8 | 00:01:25 | - | ✗ | - | 8.00 | 18,355 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0918 | 8 | 00:01:24 | - | ✗ | - | 14.00 | 21,043 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.0955 | 8 | 00:01:39 | - | ✗ | - | 12.00 | 22,347 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1018 | 8 | 00:01:41 | - | ✗ | - | 8.00 | 20,340 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1047 | 2 | 00:00:16 | - | ✗ | - | - | 3,532 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1057 | 2 | 00:00:12 | - | ✗ | - | - | 3,300 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1058 | 8 | 00:01:21 | - | ✗ | - | 14.00 | 18,680 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1117 | 8 | 00:01:29 | - | ✗ | - | 12.00 | 19,501 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1151 | 3 | 00:00:35 | - | ✗ | - | 14.00 | 5,674 | 3 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1157 | 2 | 00:00:13 | - | ✓ | ✓ | 0.00 | 3,573 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1231 | 6 | 00:01:07 | - | ✓ | ✓ | 0.00 | 14,472 | 6 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1239 | 4 | 00:00:39 | - | ✓ | ✓ | 0.00 | 9,211 | 4 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1302 | 8 | 00:02:33 | - | ✗ | ✗ | 10.00 | 20,572 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1318 | 8 | 00:01:33 | - | ✗ | ✗ | 11.00 | 20,994 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1324 | 8 | 00:02:10 | - | ✗ | ✗ | 16.00 | 22,048 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1353 | 8 | 00:01:21 | - | ✗ | ✗ | 14.00 | 20,620 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1359 | 8 | 00:01:38 | - | ✗ | ✗ | 12.00 | 22,358 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1911 | 8 | 00:01:22 | - | ✗ | ✗ | 8.00 | 19,791 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1917 | 1 | 00:00:07 | - | - | - | - | 1,668 | 1 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1918 | 1 | 00:00:09 | - | - | - | - | 1,641 | 1 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1920 | 1 | 00:00:10 | - | - | - | - | 1,782 | 1 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1926 | 1 | 00:00:09 | - | - | - | - | 1,736 | 1 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_002 | 25.079.1929 | 2 | 00:00:12 | - | ✗ | ✗ | - | 3,390 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.080.1801 | 8 | 00:01:26 | - | ✗ | ✗ | 8.00 | 20,843 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.081.1032 | 8 | 00:02:39 | - | ✗ | ✗ | 66.66 | 22,226 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.082.0630 | 2 | 00:00:13 | - | ✓ | ✓ | 0.00 | 3,607 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.082.0640 | 8 | 00:01:22 | - | ✗ | ✗ | 133.34 | 21,315 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.082.0805 | 8 | 00:01:58 | - | ✗ | ✗ | 66.66 | 25,023 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.082.0922 | 2 | 00:00:14 | - | ✓ | ✓ | 0.00 | 3,301 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.082.0927 | 2 | 00:00:19 | - | ✓ | ✓ | 0.00 | 3,623 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.082.0930 | 8 | 00:02:02 | - | ✗ | ✗ | 55.56 | 19,336 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.082.0942 | 8 | 00:02:18 | - | ✗ | ✗ | 55.56 | 22,590 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.082.1013 | 8 | 00:01:59 | - | ✗ | ✗ | 33.33 | 20,572 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.082.1228 | 8 | 00:01:41 | - | ✗ | ✗ | 66.67 | 21,122 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.083.0638 | 8 | 00:01:20 | - | ✓ | ✓ | 66.67 | 18,808 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.083.0709 | 8 | 00:01:49 | - | ✗ | - | 33.33 | 22,285 | 8 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_003 | 25.083.1007 | 6 | 00:01:01 | - | ✓ | ✓ | 0.00 | 14,716 | 6 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_005 | 25.083.1242 | 2 | 00:00:34 | - | ✓ | ✓ | 0.00 | 6,869 | 2 | 0 | gemini-2.0-pro-exp-02-05 |
| sessions_005 | 25.083.1559 | 8 | 00:01:31 | - | ✗ | ✗ | 200.00 | 24,568 | 8 | 0 | - |
| sessions_005 | 25.084.1005 | 2 | 00:00:19 | - | ✓ | ✓ | 0.00 | 5,177 | 2 | 0 | gemini-2.5-pro-exp-03-25 |
| sessions_005 | 25.085.0549 | 2 | 00:00:21 | - | ✓ | ✓ | 0.00 | 5,172 | 2 | 0 | gemini-2.5-pro-exp-03-25 |
| sessions_005 | 25.085.2031 | 2 | 00:01:01 | - | ✓ | ✗ | 22.22 | 10,644 | 2 | 0 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train | 25.095.1030 | 2 | 00:00:24 | - | ✓ | ✓ | 0.00 | 3,845 | 4 | 2 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train | 25.095.1054 | 2 | 00:00:19 | - | ✓ | ✓ | 0.00 | 3,123 | 4 | 2 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train | 25.095.1157 | 2 | 00:00:23 | - | ✓ | ✓ | 0.00 | 4,322 | 4 | 2 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train | 25.095.1238 | 2 | 00:00:18 | - | ✓ | ✓ | 0.00 | 3,233 | 4 | 2 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train | 25.095.1400 | 4 | 00:00:51 | - | ✓ | ✓ | 0.00 | 12,064 | 8 | 4 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train | 25.095.1424 | 2 | 00:00:14 | - | ✓ | ✓ | 0.00 | 3,109 | 4 | 2 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train | 25.095.1524 | 2 | 00:00:15 | - | ✓ | ✓ | 0.00 | 3,113 | 2 | 0 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train | 25.095.1710 | 2 | 00:00:18 | - | ✓ | ✓ | 0.00 | 3,412 | 2 | 0 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train | 25.100.1820 | 0 | 00:03:50 | ✗ | - | - | - | 0 | 3 | 2 | - |
| sessions_ARCv2_train | 25.100.1848 | 2 | 00:00:19 | - | ✓ | ✓ | 0.00 | 4,458 | 2 | 0 | gemini-2.5-pro-preview-03-25 |
| sessions_ARCv2_train_ | 25.095.1030 | 2 | 00:00:24 | - | ✓ | ✓ | 0.00 | 3,845 | 4 | 2 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train_ | 25.095.1054 | 2 | 00:00:19 | - | ✓ | ✓ | 0.00 | 3,123 | 4 | 2 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train_ | 25.095.1157 | 2 | 00:00:23 | - | ✓ | ✓ | 0.00 | 4,322 | 4 | 2 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train_ | 25.095.1238 | 2 | 00:00:18 | - | ✓ | ✓ | 0.00 | 3,233 | 4 | 2 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train_ | 25.095.1400 | 4 | 00:00:51 | - | ✓ | ✓ | 0.00 | 12,064 | 8 | 4 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train_ | 25.095.1424 | 2 | 00:00:14 | - | ✓ | ✓ | 0.00 | 3,109 | 4 | 2 | gemini-2.5-pro-exp-03-25 |
| sessions_ARCv2_train_ | 25.095.1524 | 2 | 00:00:15 | - | ✓ | ✓ | 0.00 | 3,113 | 4 | 2 | gemini-2.5-pro-exp-03-25 |