File size: 119,105 Bytes
d54f998 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 |
{
"results": {
"leaderboard": {
"prompt_level_loose_acc,none": 0.8059149722735675,
"prompt_level_loose_acc_stderr,none": 0.017019380550749398,
"acc_norm,none": 0.46997016474250874,
"acc_norm_stderr,none": 0.005361616709634494,
"exact_match,none": 0.1555891238670695,
"exact_match_stderr,none": 0.00951584982269579,
"acc,none": 0.38804853723404253,
"acc_stderr,none": 0.004442737468628362,
"inst_level_loose_acc,none": 0.86810551558753,
"inst_level_loose_acc_stderr,none": "N/A",
"prompt_level_strict_acc,none": 0.7763401109057301,
"prompt_level_strict_acc_stderr,none": 0.017931771054658374,
"inst_level_strict_acc,none": 0.842925659472422,
"inst_level_strict_acc_stderr,none": "N/A",
"alias": "leaderboard"
},
"leaderboard_bbh": {
"acc_norm,none": 0.5110223919458428,
"acc_norm_stderr,none": 0.0062161694547312124,
"alias": " - leaderboard_bbh"
},
"leaderboard_bbh_boolean_expressions": {
"acc_norm,none": 0.844,
"acc_norm_stderr,none": 0.022995023034068734,
"alias": " - leaderboard_bbh_boolean_expressions"
},
"leaderboard_bbh_causal_judgement": {
"acc_norm,none": 0.5989304812834224,
"acc_norm_stderr,none": 0.03593697887872985,
"alias": " - leaderboard_bbh_causal_judgement"
},
"leaderboard_bbh_date_understanding": {
"acc_norm,none": 0.444,
"acc_norm_stderr,none": 0.03148684942554575,
"alias": " - leaderboard_bbh_date_understanding"
},
"leaderboard_bbh_disambiguation_qa": {
"acc_norm,none": 0.48,
"acc_norm_stderr,none": 0.03166085340849519,
"alias": " - leaderboard_bbh_disambiguation_qa"
},
"leaderboard_bbh_formal_fallacies": {
"acc_norm,none": 0.56,
"acc_norm_stderr,none": 0.03145724452223564,
"alias": " - leaderboard_bbh_formal_fallacies"
},
"leaderboard_bbh_geometric_shapes": {
"acc_norm,none": 0.388,
"acc_norm_stderr,none": 0.030881038748993922,
"alias": " - leaderboard_bbh_geometric_shapes"
},
"leaderboard_bbh_hyperbaton": {
"acc_norm,none": 0.68,
"acc_norm_stderr,none": 0.02956172495524104,
"alias": " - leaderboard_bbh_hyperbaton"
},
"leaderboard_bbh_logical_deduction_five_objects": {
"acc_norm,none": 0.34,
"acc_norm_stderr,none": 0.030020073605457904,
"alias": " - leaderboard_bbh_logical_deduction_five_objects"
},
"leaderboard_bbh_logical_deduction_seven_objects": {
"acc_norm,none": 0.216,
"acc_norm_stderr,none": 0.026078657663732716,
"alias": " - leaderboard_bbh_logical_deduction_seven_objects"
},
"leaderboard_bbh_logical_deduction_three_objects": {
"acc_norm,none": 0.536,
"acc_norm_stderr,none": 0.03160397514522375,
"alias": " - leaderboard_bbh_logical_deduction_three_objects"
},
"leaderboard_bbh_movie_recommendation": {
"acc_norm,none": 0.496,
"acc_norm_stderr,none": 0.031685198551199154,
"alias": " - leaderboard_bbh_movie_recommendation"
},
"leaderboard_bbh_navigate": {
"acc_norm,none": 0.636,
"acc_norm_stderr,none": 0.030491555220405555,
"alias": " - leaderboard_bbh_navigate"
},
"leaderboard_bbh_object_counting": {
"acc_norm,none": 0.32,
"acc_norm_stderr,none": 0.02956172495524104,
"alias": " - leaderboard_bbh_object_counting"
},
"leaderboard_bbh_penguins_in_a_table": {
"acc_norm,none": 0.5205479452054794,
"acc_norm_stderr,none": 0.04148766180925171,
"alias": " - leaderboard_bbh_penguins_in_a_table"
},
"leaderboard_bbh_reasoning_about_colored_objects": {
"acc_norm,none": 0.632,
"acc_norm_stderr,none": 0.03056207062099316,
"alias": " - leaderboard_bbh_reasoning_about_colored_objects"
},
"leaderboard_bbh_ruin_names": {
"acc_norm,none": 0.676,
"acc_norm_stderr,none": 0.02965829492454558,
"alias": " - leaderboard_bbh_ruin_names"
},
"leaderboard_bbh_salient_translation_error_detection": {
"acc_norm,none": 0.54,
"acc_norm_stderr,none": 0.031584653891499,
"alias": " - leaderboard_bbh_salient_translation_error_detection"
},
"leaderboard_bbh_snarks": {
"acc_norm,none": 0.7303370786516854,
"acc_norm_stderr,none": 0.03335689818443928,
"alias": " - leaderboard_bbh_snarks"
},
"leaderboard_bbh_sports_understanding": {
"acc_norm,none": 0.792,
"acc_norm_stderr,none": 0.02572139890141639,
"alias": " - leaderboard_bbh_sports_understanding"
},
"leaderboard_bbh_temporal_sequences": {
"acc_norm,none": 0.508,
"acc_norm_stderr,none": 0.031682156431413803,
"alias": " - leaderboard_bbh_temporal_sequences"
},
"leaderboard_bbh_tracking_shuffled_objects_five_objects": {
"acc_norm,none": 0.26,
"acc_norm_stderr,none": 0.02779731575264431,
"alias": " - leaderboard_bbh_tracking_shuffled_objects_five_objects"
},
"leaderboard_bbh_tracking_shuffled_objects_seven_objects": {
"acc_norm,none": 0.248,
"acc_norm_stderr,none": 0.027367497504863555,
"alias": " - leaderboard_bbh_tracking_shuffled_objects_seven_objects"
},
"leaderboard_bbh_tracking_shuffled_objects_three_objects": {
"acc_norm,none": 0.36,
"acc_norm_stderr,none": 0.03041876402517499,
"alias": " - leaderboard_bbh_tracking_shuffled_objects_three_objects"
},
"leaderboard_bbh_web_of_lies": {
"acc_norm,none": 0.548,
"acc_norm_stderr,none": 0.03153986449255662,
"alias": " - leaderboard_bbh_web_of_lies"
},
"leaderboard_gpqa": {
"acc_norm,none": 0.30956375838926176,
"acc_norm_stderr,none": 0.013399833124685697,
"alias": " - leaderboard_gpqa"
},
"leaderboard_gpqa_diamond": {
"acc_norm,none": 0.2777777777777778,
"acc_norm_stderr,none": 0.031911782267135466,
"alias": " - leaderboard_gpqa_diamond"
},
"leaderboard_gpqa_extended": {
"acc_norm,none": 0.30952380952380953,
"acc_norm_stderr,none": 0.019802641880170335,
"alias": " - leaderboard_gpqa_extended"
},
"leaderboard_gpqa_main": {
"acc_norm,none": 0.3236607142857143,
"acc_norm_stderr,none": 0.02212959876820087,
"alias": " - leaderboard_gpqa_main"
},
"leaderboard_ifeval": {
"prompt_level_strict_acc,none": 0.7763401109057301,
"prompt_level_strict_acc_stderr,none": 0.017931771054658374,
"inst_level_strict_acc,none": 0.842925659472422,
"inst_level_strict_acc_stderr,none": "N/A",
"prompt_level_loose_acc,none": 0.8059149722735675,
"prompt_level_loose_acc_stderr,none": 0.017019380550749398,
"inst_level_loose_acc,none": 0.86810551558753,
"inst_level_loose_acc_stderr,none": "N/A",
"alias": " - leaderboard_ifeval"
},
"leaderboard_math_hard": {
"exact_match,none": 0.1555891238670695,
"exact_match_stderr,none": 0.00951584982269579,
"alias": " - leaderboard_math_hard"
},
"leaderboard_math_algebra_hard": {
"exact_match,none": 0.2671009771986971,
"exact_match_stderr,none": 0.02529292734708582,
"alias": " - leaderboard_math_algebra_hard"
},
"leaderboard_math_counting_and_prob_hard": {
"exact_match,none": 0.08943089430894309,
"exact_match_stderr,none": 0.025835705603547247,
"alias": " - leaderboard_math_counting_and_prob_hard"
},
"leaderboard_math_geometry_hard": {
"exact_match,none": 0.09090909090909091,
"exact_match_stderr,none": 0.025117225636160798,
"alias": " - leaderboard_math_geometry_hard"
},
"leaderboard_math_intermediate_algebra_hard": {
"exact_match,none": 0.04285714285714286,
"exact_match_stderr,none": 0.012125450612513616,
"alias": " - leaderboard_math_intermediate_algebra_hard"
},
"leaderboard_math_num_theory_hard": {
"exact_match,none": 0.13636363636363635,
"exact_match_stderr,none": 0.027743997176957885,
"alias": " - leaderboard_math_num_theory_hard"
},
"leaderboard_math_prealgebra_hard": {
"exact_match,none": 0.32642487046632124,
"exact_match_stderr,none": 0.03384028621143295,
"alias": " - leaderboard_math_prealgebra_hard"
},
"leaderboard_math_precalculus_hard": {
"exact_match,none": 0.037037037037037035,
"exact_match_stderr,none": 0.016314377626726044,
"alias": " - leaderboard_math_precalculus_hard"
},
"leaderboard_mmlu_pro": {
"acc,none": 0.38804853723404253,
"acc_stderr,none": 0.004442737468628362,
"alias": " - leaderboard_mmlu_pro"
},
"leaderboard_musr": {
"acc_norm,none": 0.41005291005291006,
"acc_norm_stderr,none": 0.017287766402497906,
"alias": " - leaderboard_musr"
},
"leaderboard_musr_murder_mysteries": {
"acc_norm,none": 0.592,
"acc_norm_stderr,none": 0.03114520984654851,
"alias": " - leaderboard_musr_murder_mysteries"
},
"leaderboard_musr_object_placements": {
"acc_norm,none": 0.29296875,
"acc_norm_stderr,none": 0.028500984607927556,
"alias": " - leaderboard_musr_object_placements"
},
"leaderboard_musr_team_allocation": {
"acc_norm,none": 0.348,
"acc_norm_stderr,none": 0.030186568464511686,
"alias": " - leaderboard_musr_team_allocation"
}
},
"groups": {
"leaderboard": {
"prompt_level_loose_acc,none": 0.8059149722735675,
"prompt_level_loose_acc_stderr,none": 0.017019380550749398,
"acc_norm,none": 0.46997016474250874,
"acc_norm_stderr,none": 0.005361616709634494,
"exact_match,none": 0.1555891238670695,
"exact_match_stderr,none": 0.00951584982269579,
"acc,none": 0.38804853723404253,
"acc_stderr,none": 0.004442737468628362,
"inst_level_loose_acc,none": 0.86810551558753,
"inst_level_loose_acc_stderr,none": "N/A",
"prompt_level_strict_acc,none": 0.7763401109057301,
"prompt_level_strict_acc_stderr,none": 0.017931771054658374,
"inst_level_strict_acc,none": 0.842925659472422,
"inst_level_strict_acc_stderr,none": "N/A",
"alias": "leaderboard"
},
"leaderboard_bbh": {
"acc_norm,none": 0.5110223919458428,
"acc_norm_stderr,none": 0.0062161694547312124,
"alias": " - leaderboard_bbh"
},
"leaderboard_gpqa": {
"acc_norm,none": 0.30956375838926176,
"acc_norm_stderr,none": 0.013399833124685697,
"alias": " - leaderboard_gpqa"
},
"leaderboard_math_hard": {
"exact_match,none": 0.1555891238670695,
"exact_match_stderr,none": 0.00951584982269579,
"alias": " - leaderboard_math_hard"
},
"leaderboard_musr": {
"acc_norm,none": 0.41005291005291006,
"acc_norm_stderr,none": 0.017287766402497906,
"alias": " - leaderboard_musr"
}
},
"group_subtasks": {
"leaderboard_bbh": [
"leaderboard_bbh_sports_understanding",
"leaderboard_bbh_object_counting",
"leaderboard_bbh_geometric_shapes",
"leaderboard_bbh_hyperbaton",
"leaderboard_bbh_disambiguation_qa",
"leaderboard_bbh_logical_deduction_three_objects",
"leaderboard_bbh_causal_judgement",
"leaderboard_bbh_tracking_shuffled_objects_seven_objects",
"leaderboard_bbh_temporal_sequences",
"leaderboard_bbh_web_of_lies",
"leaderboard_bbh_formal_fallacies",
"leaderboard_bbh_salient_translation_error_detection",
"leaderboard_bbh_tracking_shuffled_objects_five_objects",
"leaderboard_bbh_ruin_names",
"leaderboard_bbh_logical_deduction_five_objects",
"leaderboard_bbh_penguins_in_a_table",
"leaderboard_bbh_movie_recommendation",
"leaderboard_bbh_snarks",
"leaderboard_bbh_boolean_expressions",
"leaderboard_bbh_navigate",
"leaderboard_bbh_date_understanding",
"leaderboard_bbh_reasoning_about_colored_objects",
"leaderboard_bbh_logical_deduction_seven_objects",
"leaderboard_bbh_tracking_shuffled_objects_three_objects"
],
"leaderboard_gpqa": [
"leaderboard_gpqa_main",
"leaderboard_gpqa_extended",
"leaderboard_gpqa_diamond"
],
"leaderboard_math_hard": [
"leaderboard_math_intermediate_algebra_hard",
"leaderboard_math_counting_and_prob_hard",
"leaderboard_math_algebra_hard",
"leaderboard_math_num_theory_hard",
"leaderboard_math_precalculus_hard",
"leaderboard_math_geometry_hard",
"leaderboard_math_prealgebra_hard"
],
"leaderboard_musr": [
"leaderboard_musr_murder_mysteries",
"leaderboard_musr_team_allocation",
"leaderboard_musr_object_placements"
],
"leaderboard": [
"leaderboard_musr",
"leaderboard_ifeval",
"leaderboard_math_hard",
"leaderboard_gpqa",
"leaderboard_bbh",
"leaderboard_mmlu_pro"
]
},
"configs": {
"leaderboard_bbh_boolean_expressions": {
"task": "leaderboard_bbh_boolean_expressions",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "boolean_expressions",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"False",
"True"
],
"description": "Evaluate the result of a random Boolean expression.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "not ( ( not not True ) ) is",
"target": "False"
},
{
"input": "True and False and not True and True is",
"target": "False"
},
{
"input": "not not ( not ( False ) ) is",
"target": "True"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_causal_judgement": {
"task": "leaderboard_bbh_causal_judgement",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "causal_judgement",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"Yes",
"No"
],
"description": "Answer questions about causal attribution.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "How would a typical person answer each of the following questions about causation?\nFrank T., had an ongoing dispute with his neighbor over a stretch of land and one day decided to shoot his neighbor in the body. Frank T. had no experience with guns, his hand slipped on the barrel of the gun, and the shot went wild. Nonetheless, the bullet bounced off a large boulder several feet away and hit the neighbor's body, causing significant injury. Did Frank T. intentionally shoot his neighbor in the body?\nOptions:\n- Yes\n- No",
"target": "No"
},
{
"input": "How would a typical person answer each of the following questions about causation?\nSuzy and Billy are working on a project that is very important for our nation's security. The boss tells them both: \"Be sure that you are here at exactly 9 am. It is absolutely essential that you arrive at that time.\" Both Billy and Suzy arrive at 9 am. As it happens, there was a motion detector installed in the room where they arrived. The motion detector was set up to be triggered if at least one person appeared in the room at the same time. So the motion detector went off. Did Billy cause the motion detector to go off?\nOptions:\n- Yes\n- No",
"target": "Yes"
},
{
"input": "How would a typical person answer each of the following questions about causation?\nGeorge and his sister Lena reunite at their parents' house for Thanksgiving. Whereas George just got into medical school, Lena is unhappy in her marriage and recently lost her job. Over the course of the day, George and Lena get into a number of heated arguments. Later in the afternoon they play a game of darts. They split the first two games, and the third game is close until the end. Who will win comes down to George's last shot. If he hits a high point region, he wins; if he hits a low point region, Lena wins. George thinks of the difficult time Lena is having, and he really wants to let her win. He aims the dart at the low point region. He sets up his shot and the dart lands in the low point region. After his shot, Lena wins the game and is very happy. Did George hit the low point region intentionally?\nOptions:\n- Yes\n- No",
"target": "Yes"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_date_understanding": {
"task": "leaderboard_bbh_date_understanding",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "date_understanding",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)",
"(E)",
"(F)"
],
"description": "Infer the date from context.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "Today is Christmas Eve of 1937. What is the date 10 days ago in MM/DD/YYYY?\nOptions:\n(A) 12/14/2026\n(B) 12/14/1950\n(C) 12/14/2007\n(D) 12/14/1937\n(E) 07/14/1938\n(F) 12/14/1988",
"target": "(D)"
},
{
"input": "Tomorrow is 11/12/2019. What is the date one year ago from today in MM/DD/YYYY?\nOptions:\n(A) 09/04/2018\n(B) 11/11/2018\n(C) 08/25/2018\n(D) 11/02/2018\n(E) 11/04/2018",
"target": "(B)"
},
{
"input": "Jane and John married on Jan 2, 1958. It is their 5-year anniversary today. What is the date tomorrow in MM/DD/YYYY?\nOptions:\n(A) 01/11/1961\n(B) 01/03/1963\n(C) 01/18/1961\n(D) 10/14/1960\n(E) 01/03/1982\n(F) 12/03/1960",
"target": "(B)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_disambiguation_qa": {
"task": "leaderboard_bbh_disambiguation_qa",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "disambiguation_qa",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)"
],
"description": "Clarify the meaning of sentences with ambiguous pronouns.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "In the following sentences, explain the antecedent of the pronoun (which thing the pronoun refers to), or state that it is ambiguous.\nSentence: The chief told the counselor that they took the day off.\nOptions:\n(A) The chief took the day off\n(B) The counselor took the day off\n(C) Ambiguous",
"target": "(A)"
},
{
"input": "In the following sentences, explain the antecedent of the pronoun (which thing the pronoun refers to), or state that it is ambiguous.\nSentence: The manager sent a message to the secretary, but he didn't reply yet.\nOptions:\n(A) The secretary didn't reply yet\n(B) The manager didn't reply yet\n(C) Ambiguous",
"target": "(A)"
},
{
"input": "In the following sentences, explain the antecedent of the pronoun (which thing the pronoun refers to), or state that it is ambiguous.\nSentence: Bailey will plan to meet the director at his office\nOptions:\n(A) It will be Bailey's office\n(B) It will be the director's office\n(C) Ambiguous",
"target": "(C)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_formal_fallacies": {
"task": "leaderboard_bbh_formal_fallacies",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "formal_fallacies",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"valid",
"invalid"
],
"description": "Distinguish deductively valid arguments from formal fallacies.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "\"It is not always easy to see who is related to whom -- and in which ways. The following argument pertains to this question: To begin with, Lesley is a close friend of Fernando. Moreover, being a close friend of Fernando or a schoolmate of Lowell is sufficient for being a great-grandfather of Leroy. It follows that Lesley is a great-grandfather of Leroy.\"\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\nOptions:\n- valid\n- invalid",
"target": "valid"
},
{
"input": "\"It is not always easy to see who is related to whom -- and in which ways. The following argument pertains to this question: Whoever is not a great-grandfather of Clyde is a stepbrother of Brian. Being an ancestor of Dana is sufficient for not being a great-grandfather of Clyde. We may conclude: Everyone who is an ancestor of Dana is a stepbrother of Brian, too.\"\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\nOptions:\n- valid\n- invalid",
"target": "valid"
},
{
"input": "\"It is not always easy to grasp who is consuming which products. The following argument pertains to this question: Every infrequent user of Paul Mitchell shampoo is either a rare consumer of Nioxin shampoo or a loyal buyer of Caress soap, or both. No regular consumer of Lush soap is a rare consumer of Nioxin shampoo and, in the same time, a loyal buyer of Caress soap. It follows that whoever is an infrequent user of Paul Mitchell shampoo is not a regular consumer of Lush soap.\"\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\nOptions:\n- valid\n- invalid",
"target": "invalid"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_geometric_shapes": {
"task": "leaderboard_bbh_geometric_shapes",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "geometric_shapes",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)",
"(E)",
"(F)",
"(G)",
"(H)",
"(I)",
"(J)",
"(K)"
],
"description": "Name geometric shapes from their SVG paths.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "This SVG path element <path d=\"M 31.00,73.00 L 32.00,59.00 L 44.00,50.00 L 49.00,41.00 L 64.00,37.00 L 71.00,55.00 L 64.00,76.00 L 52.00,61.00 L 31.00,73.00\"/> draws a\nOptions:\n(A) circle\n(B) heptagon\n(C) hexagon\n(D) kite\n(E) line\n(F) octagon\n(G) pentagon\n(H) rectangle\n(I) sector\n(J) triangle",
"target": "(F)"
},
{
"input": "This SVG path element <path d=\"M 14.19,26.04 L 51.43,39.21 L 58.44,36.69 L 56.63,30.17 L 48.53,26.66 L 14.19,26.04\"/> draws a\nOptions:\n(A) circle\n(B) heptagon\n(C) hexagon\n(D) kite\n(E) line\n(F) octagon\n(G) pentagon\n(H) rectangle\n(I) sector\n(J) triangle",
"target": "(G)"
},
{
"input": "This SVG path element <path d=\"M 41.00,43.00 L 37.00,34.00 L 41.00,33.00 L 45.00,34.00 L 41.00,43.00\"/> draws a\nOptions:\n(A) circle\n(B) heptagon\n(C) hexagon\n(D) kite\n(E) line\n(F) octagon\n(G) pentagon\n(H) rectangle\n(I) sector\n(J) triangle",
"target": "(D)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_hyperbaton": {
"task": "leaderboard_bbh_hyperbaton",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "hyperbaton",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)"
],
"description": "Order adjectives correctly in English sentences.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "Which sentence has the correct adjective order:\nOptions:\n(A) rubber terrible ship\n(B) terrible rubber ship",
"target": "(B)"
},
{
"input": "Which sentence has the correct adjective order:\nOptions:\n(A) repulsive small Brazilian exercise ship\n(B) Brazilian repulsive exercise small ship",
"target": "(A)"
},
{
"input": "Which sentence has the correct adjective order:\nOptions:\n(A) blue gold wonderful square shoe\n(B) wonderful square blue gold shoe",
"target": "(B)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_logical_deduction_five_objects": {
"task": "leaderboard_bbh_logical_deduction_five_objects",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "logical_deduction_five_objects",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)",
"(E)"
],
"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished above Amy. Eli finished below Amy.\nOptions:\n(A) Amy finished last\n(B) Eli finished last\n(C) Eve finished last",
"target": "(B)"
},
{
"input": "The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a white book, a green book, and an orange book. The green book is to the right of the white book. The orange book is the rightmost.\nOptions:\n(A) The white book is the leftmost\n(B) The green book is the leftmost\n(C) The orange book is the leftmost",
"target": "(A)"
},
{
"input": "The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a red book, a gray book, and a white book. The white book is to the left of the gray book. The red book is the second from the left.\nOptions:\n(A) The red book is the leftmost\n(B) The gray book is the leftmost\n(C) The white book is the leftmost",
"target": "(C)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_logical_deduction_seven_objects": {
"task": "leaderboard_bbh_logical_deduction_seven_objects",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "logical_deduction_seven_objects",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)",
"(E)",
"(F)",
"(G)"
],
"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished above Amy. Eli finished below Amy.\nOptions:\n(A) Amy finished last\n(B) Eli finished last\n(C) Eve finished last",
"target": "(B)"
},
{
"input": "The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a white book, a green book, and an orange book. The green book is to the right of the white book. The orange book is the rightmost.\nOptions:\n(A) The white book is the leftmost\n(B) The green book is the leftmost\n(C) The orange book is the leftmost",
"target": "(A)"
},
{
"input": "The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a red book, a gray book, and a white book. The white book is to the left of the gray book. The red book is the second from the left.\nOptions:\n(A) The red book is the leftmost\n(B) The gray book is the leftmost\n(C) The white book is the leftmost",
"target": "(C)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_logical_deduction_three_objects": {
"task": "leaderboard_bbh_logical_deduction_three_objects",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "logical_deduction_three_objects",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)"
],
"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished above Amy. Eli finished below Amy.\nOptions:\n(A) Amy finished last\n(B) Eli finished last\n(C) Eve finished last",
"target": "(B)"
},
{
"input": "The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a white book, a green book, and an orange book. The green book is to the right of the white book. The orange book is the rightmost.\nOptions:\n(A) The white book is the leftmost\n(B) The green book is the leftmost\n(C) The orange book is the leftmost",
"target": "(A)"
},
{
"input": "The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a red book, a gray book, and a white book. The white book is to the left of the gray book. The red book is the second from the left.\nOptions:\n(A) The red book is the leftmost\n(B) The gray book is the leftmost\n(C) The white book is the leftmost",
"target": "(C)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_movie_recommendation": {
"task": "leaderboard_bbh_movie_recommendation",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "movie_recommendation",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)",
"(E)",
"(F)"
],
"description": "Recommend movies similar to the given list of movies.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "Find a movie similar to Star Wars Episode IV - A New Hope, Indiana Jones and the Last Crusade, Star Wars Episode V - The Empire Strikes Back, The Big Lebowski:\nOptions:\n(A) Tetsuo\n(B) the Ironman\n(C) The Princess Bride\n(D) The Barkley Marathons The Race That Eats Its Young\n(E) Bug",
"target": "(C)"
},
{
"input": "Find a movie similar to Twister, The Silence of the Lambs, Independence Day, Braveheart:\nOptions:\n(A) They Shoot Horses\n(B) Don't They\n(C) Forrest Gump\n(D) The Salton Sea\n(E) Extreme Days",
"target": "(C)"
},
{
"input": "Find a movie similar to Minority Report, Total Recall, Inside Out, Forrest Gump:\nOptions:\n(A) Phenomena\n(B) Lilting\n(C) Catwoman\n(D) Edge of Tomorrow",
"target": "(D)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_navigate": {
"task": "leaderboard_bbh_navigate",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "navigate",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"Yes",
"No"
],
"description": "Given a series of navigation instructions, determine whether one would end up back at the starting point.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "If you follow these instructions, do you return to the starting point? Turn left. Turn around. Turn left. Take 7 steps. Take 2 steps. Take 4 steps. Take 8 steps.\nOptions:\n- Yes\n- No",
"target": "No"
},
{
"input": "If you follow these instructions, do you return to the starting point? Turn around. Take 1 step. Take 6 steps. Turn around. Take 6 steps. Take 9 steps. Take 1 step.\nOptions:\n- Yes\n- No",
"target": "No"
},
{
"input": "If you follow these instructions, do you return to the starting point? Always face forward. Take 2 steps right. Take 9 steps left. Take 7 steps right.\nOptions:\n- Yes\n- No",
"target": "Yes"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_object_counting": {
"task": "leaderboard_bbh_object_counting",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "object_counting",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"0",
"1",
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"10",
"11",
"12",
"13",
"14",
"15",
"16",
"17",
"18"
],
"description": "Questions that involve enumerating objects and asking the model to count them.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "I have a blackberry, a clarinet, a nectarine, a plum, a strawberry, a banana, a flute, an orange, and a violin. How many fruits do I have?",
"target": "6"
},
{
"input": "I have an orange, a raspberry, two peaches, a blackberry, an apple, a grape, a nectarine, and three plums. How many fruits do I have?",
"target": "11"
},
{
"input": "I have a lettuce head, a head of broccoli, an onion, a stalk of celery, two carrots, a garlic, and a yam. How many vegetables do I have?",
"target": "8"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_penguins_in_a_table": {
"task": "leaderboard_bbh_penguins_in_a_table",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "penguins_in_a_table",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)",
"(E)"
],
"description": "Answer questions about a table of penguins and their attributes.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "Here is a table where the first line is a header and each subsequent line is a penguin: name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard, 5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15 For example: the age of Louis is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm. We now add a penguin to the table:\nJames, 12, 90, 12\nHow many penguins are less than 8 years old?\nOptions:\n(A) 1\n(B) 2\n(C) 3\n(D) 4\n(E) 5",
"target": "(B)"
},
{
"input": "Here is a table where the first line is a header and each subsequent line is a penguin: name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard, 5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15 For example: the age of Louis is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm. Which is the youngest penguin?\nOptions:\n(A) Louis\n(B) Bernard\n(C) Vincent\n(D) Gwen\n(E) James",
"target": "(B)"
},
{
"input": "Here is a table where the first line is a header and each subsequent line is a penguin: name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard, 5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15 For example: the age of Louis is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm. What is the name of the second penguin sorted by alphabetic order?\nOptions:\n(A) Louis\n(B) Bernard\n(C) Vincent\n(D) Gwen\n(E) James",
"target": "(D)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_reasoning_about_colored_objects": {
"task": "leaderboard_bbh_reasoning_about_colored_objects",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "reasoning_about_colored_objects",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)",
"(E)",
"(F)",
"(G)",
"(H)",
"(I)",
"(J)",
"(K)",
"(L)",
"(M)",
"(N)",
"(O)",
"(P)",
"(Q)",
"(R)"
],
"description": "Answer extremely simple questions about the colors of objects on a surface.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "On the nightstand, there is a red pencil, a purple mug, a burgundy keychain, a fuchsia teddy bear, a black plate, and a blue stress ball. What color is the stress ball?\nOptions:\n(A) red\n(B) orange\n(C) yellow\n(D) green\n(E) blue\n(F) brown\n(G) magenta\n(H) fuchsia\n(I) mauve\n(J) teal\n(K) turquoise\n(L) burgundy\n(M) silver\n(N) gold\n(O) black\n(P) grey\n(Q) purple\n(R) pink",
"target": "(E)"
},
{
"input": "On the table, you see a bunch of objects arranged in a row: a purple paperclip, a pink stress ball, a brown keychain, a green scrunchiephone charger, a mauve fidget spinner, and a burgundy pen. What is the color of the object directly to the right of the stress ball?\nOptions:\n(A) red\n(B) orange\n(C) yellow\n(D) green\n(E) blue\n(F) brown\n(G) magenta\n(H) fuchsia\n(I) mauve\n(J) teal\n(K) turquoise\n(L) burgundy\n(M) silver\n(N) gold\n(O) black\n(P) grey\n(Q) purple\n(R) pink",
"target": "(F)"
},
{
"input": "On the nightstand, you see the following items arranged in a row: a teal plate, a burgundy keychain, a yellow scrunchiephone charger, an orange mug, a pink notebook, and a grey cup. How many non-orange items do you see to the left of the teal item?\nOptions:\n(A) zero\n(B) one\n(C) two\n(D) three\n(E) four\n(F) five\n(G) six",
"target": "(A)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_ruin_names": {
"task": "leaderboard_bbh_ruin_names",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "ruin_names",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)",
"(E)",
"(F)"
],
"description": "Select the humorous edit that 'ruins' the input movie or musical artist name.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "Which of the following is a humorous edit of this artist or movie name: 'whitesnake'?\nOptions:\n(A) whitesnape\n(B) whitesnapke\n(C) whitesnuake\n(D) mwhitesnake",
"target": "(A)"
},
{
"input": "Which of the following is a humorous edit of this artist or movie name: 'one of our dinosaurs is missing'?\nOptions:\n(A) ofne of our dinosaurs is missing\n(B) one af our dinosaurs is missing\n(C) one of our dinosaurs is pissing\n(D) one of our dinosaur is missing",
"target": "(C)"
},
{
"input": "Which of the following is a humorous edit of this artist or movie name: 'counting crows'?\nOptions:\n(A) countingy crows\n(B) counting cows\n(C) courting crows\n(D) coutnting crows",
"target": "(B)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_salient_translation_error_detection": {
"task": "leaderboard_bbh_salient_translation_error_detection",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "salient_translation_error_detection",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)",
"(E)",
"(F)"
],
"description": "Detect the type of error in an English translation of a German source sentence.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "The following translations from German to English contain a particular error. That error will be one of the following types: Named Entities: An entity (names, places, locations, etc.) is changed to a different entity. Numerical Values: Numerical values (ordinals or cardinals), dates, and/or units are changed. Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are changed. Negation or Antonyms: Introduce or remove a negation or change comparatives to their antonyms. Facts: Trivial factual errors not pertaining to the above classes are introduced in the translations. Dropped Content: A significant clause in the translation is removed. Please identify that error. Source: In der Liste der Baudenkmale in Lenzen (Elbe) sind alle Baudenkmale der brandenburgischen Stadt Lenzen (Elbe) und ihrer Ortsteile aufgelistet.\nTranslation: In the list of architectural monuments in Lenzen all architectural monuments of the Brandenburg city of Lenzen and its districts are listed.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts",
"target": "(D)"
},
{
"input": "The following translations from German to English contain a particular error. That error will be one of the following types: Named Entities: An entity (names, places, locations, etc.) is changed to a different entity. Numerical Values: Numerical values (ordinals or cardinals), dates, and/or units are changed. Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are changed. Negation or Antonyms: Introduce or remove a negation or change comparatives to their antonyms. Facts: Trivial factual errors not pertaining to the above classes are introduced in the translations. Dropped Content: A significant clause in the translation is removed. Please identify that error. Source: Auf dieser Seite sind die Baudenkmäler der oberbayerischen Großen Kreisstadt Landsberg am Lech zusammengestellt.\nTranslation: On this page are compiled the architectural monuments of the town of Landsberg am Lech.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts",
"target": "(E)"
},
{
"input": "The following translations from German to English contain a particular error. That error will be one of the following types: Named Entities: An entity (names, places, locations, etc.) is changed to a different entity. Numerical Values: Numerical values (ordinals or cardinals), dates, and/or units are changed. Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are changed. Negation or Antonyms: Introduce or remove a negation or change comparatives to their antonyms. Facts: Trivial factual errors not pertaining to the above classes are introduced in the translations. Dropped Content: A significant clause in the translation is removed. Please identify that error. Source: Łeba ist eine Kleinstadt und ein Badeort im Powiat Lęborski der polnischen Woiwodschaft Pommern.\nTranslation: Eba is not a small town and seaside resort in the Powiat Léborski county of the Pomeranian Voivodeship of Poland.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts",
"target": "(C)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_snarks": {
"task": "leaderboard_bbh_snarks",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "snarks",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)"
],
"description": "Determine which of two sentences is sarcastic.\n\nAccording to Cambridge University Dictionary, sarcasm is \"the use of remarks that clearly mean the opposite of what they say, made in order to hurt someone's feelings or to criticize something in a humorous way.\" Sarcastic sentences often contain satirical or ironic utterances, hyperboles, ambivalent or witty remarks.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "Which statement is sarcastic?\nOptions:\n(A) Yes, because having interests and actively researching them is a huge waste\n(B) Yes, because having interests and actively researching them is a huge deal",
"target": "(A)"
},
{
"input": "Which statement is sarcastic?\nOptions:\n(A) No one is going to disagree with you on this. Avoiding ad hominem attacks really help your case\n(B) No one is going to disagree with you on this. Ad hominem attacks really help your case",
"target": "(B)"
},
{
"input": "Which statement is sarcastic?\nOptions:\n(A) Consistency in the league's punishments? What do you think this is supposed to be, politics?\n(B) Consistency in the league's punishments? What do you think this is supposed to be, moral?",
"target": "(A)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_sports_understanding": {
"task": "leaderboard_bbh_sports_understanding",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "sports_understanding",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"yes",
"no"
],
"description": "Determine whether an artificially constructed sentence relating to sports is plausible or not.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "Is the following sentence plausible? \"Bam Adebayo scored a reverse layup in the Western Conference Finals.\"",
"target": "yes"
},
{
"input": "Is the following sentence plausible? \"Santi Cazorla scored a touchdown.\"",
"target": "no"
},
{
"input": "Is the following sentence plausible? \"DeMar DeRozan was called for the goal tend.\"",
"target": "yes"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_temporal_sequences": {
"task": "leaderboard_bbh_temporal_sequences",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "temporal_sequences",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)"
],
"description": "Task description: Answer questions about which times certain events could have occurred.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "Today, Emily went to the museum. Between what times could they have gone?\nWe know that:\nEmily woke up at 1pm.\nElizabeth saw Emily reading at the library from 2pm to 4pm.\nJessica saw Emily watching a movie at the theater from 4pm to 5pm.\nLeslie saw Emily waiting at the airport from 5pm to 6pm.\nWilliam saw Emily buying clothes at the mall from 6pm to 7pm.\nThe museum was closed after 7pm.\nBetween what times could Emily have gone to the museum?\nOptions:\n(A) 1pm to 2pm\n(B) 6pm to 7pm\n(C) 5pm to 6pm\n(D) 2pm to 4pm",
"target": "(A)"
},
{
"input": "Today, Elizabeth went to the amusement park. Between what times could they have gone?\nWe know that:\nElizabeth woke up at 7am.\nDavid saw Elizabeth fixing their computer at the electronic store from 1pm to 2pm.\nSarah saw Elizabeth playing tennis at the tennis court from 2pm to 3pm.\nSusan saw Elizabeth walking towards the Statue of Liberty from 3pm to 6pm.\nAndrew saw Elizabeth taking photos near the Eiffel Tower from 6pm to 9pm.\nEmily saw Elizabeth getting a coffee at the cafe from 9pm to 10pm.\nThe amusement park was closed after 10pm.\nBetween what times could Elizabeth have gone to the amusement park?\nOptions:\n(A) 7am to 1pm\n(B) 9pm to 10pm\n(C) 1pm to 2pm\n(D) 3pm to 6pm",
"target": "(A)"
},
{
"input": "Today, Tiffany went to the beach. Between what times could they have gone?\nWe know that:\nTiffany woke up at 5am.\nBetty saw Tiffany getting a coffee at the cafe from 5am to 6am.\nJessica saw Tiffany working at the office from 6am to 9am.\nJohn saw Tiffany stretching at a yoga studio from 9am to 12pm.\nSean saw Tiffany sitting on a rooftop from 12pm to 2pm.\nSarah saw Tiffany playing tennis at the tennis court from 2pm to 3pm.\nThe beach was closed after 4pm.\nBetween what times could Tiffany have gone to the beach?\nOptions:\n(A) 9am to 12pm\n(B) 12pm to 2pm\n(C) 5am to 6am\n(D) 3pm to 4pm",
"target": "(D)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_tracking_shuffled_objects_five_objects": {
"task": "leaderboard_bbh_tracking_shuffled_objects_five_objects",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "tracking_shuffled_objects_five_objects",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)",
"(E)"
],
"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Claire and Alice swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls. At the end of the game, Bob has the\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball",
"target": "(A)"
},
{
"input": "Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a white ball, Bob has a purple ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Bob and Alice swap balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At the end of the game, Alice has the\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball",
"target": "(C)"
},
{
"input": "Alice, Bob, and Claire are dancers at a square dance. At the start of a song, they each have a partner: Alice is dancing with Lola, Bob is dancing with Rodrigo, and Claire is dancing with Patrick.\nThroughout the song, the dancers often trade partners. First, Alice and Bob switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice switch partners. At the end of the dance, Alice is dancing with\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick",
"target": "(C)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_tracking_shuffled_objects_seven_objects": {
"task": "leaderboard_bbh_tracking_shuffled_objects_seven_objects",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "tracking_shuffled_objects_seven_objects",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)",
"(E)",
"(F)",
"(G)"
],
"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Claire and Alice swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls. At the end of the game, Bob has the\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball",
"target": "(A)"
},
{
"input": "Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a white ball, Bob has a purple ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Bob and Alice swap balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At the end of the game, Alice has the\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball",
"target": "(C)"
},
{
"input": "Alice, Bob, and Claire are dancers at a square dance. At the start of a song, they each have a partner: Alice is dancing with Lola, Bob is dancing with Rodrigo, and Claire is dancing with Patrick.\nThroughout the song, the dancers often trade partners. First, Alice and Bob switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice switch partners. At the end of the dance, Alice is dancing with\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick",
"target": "(C)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_tracking_shuffled_objects_three_objects": {
"task": "leaderboard_bbh_tracking_shuffled_objects_three_objects",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "tracking_shuffled_objects_three_objects",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"(A)",
"(B)",
"(C)"
],
"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Claire and Alice swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls. At the end of the game, Bob has the\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball",
"target": "(A)"
},
{
"input": "Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a white ball, Bob has a purple ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Bob and Alice swap balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At the end of the game, Alice has the\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball",
"target": "(C)"
},
{
"input": "Alice, Bob, and Claire are dancers at a square dance. At the start of a song, they each have a partner: Alice is dancing with Lola, Bob is dancing with Rodrigo, and Claire is dancing with Patrick.\nThroughout the song, the dancers often trade partners. First, Alice and Bob switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice switch partners. At the end of the dance, Alice is dancing with\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick",
"target": "(C)"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_bbh_web_of_lies": {
"task": "leaderboard_bbh_web_of_lies",
"group": "leaderboard_bbh",
"dataset_path": "SaylorTwift/bbh",
"dataset_name": "web_of_lies",
"test_split": "test",
"doc_to_text": "Q: {{input}}\nA:",
"doc_to_target": "{{target}}",
"doc_to_choice": [
"Yes",
"No"
],
"description": "Evaluate a random boolean function expressed as a word problem.\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": [
{
"input": "Question: Fidel tells the truth. Jerry says Fidel tells the truth. Vina says Jerry tells the truth. Millicent says Vina lies. Raymond says Millicent lies. Does Raymond tell the truth?",
"target": "Yes"
},
{
"input": "Question: Kristian lies. Millie says Kristian lies. Maybelle says Millie tells the truth. Fidel says Maybelle lies. Leda says Fidel lies. Does Leda tell the truth?",
"target": "Yes"
},
{
"input": "Question: Kristian tells the truth. Michaela says Kristian lies. Raymond says Michaela tells the truth. Osvaldo says Raymond tells the truth. Jamey says Osvaldo tells the truth. Does Jamey tell the truth?",
"target": "No"
}
]
},
"num_fewshot": 3,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.0
}
},
"leaderboard_gpqa_diamond": {
"task": "leaderboard_gpqa_diamond",
"group": "leaderboard_gpqa",
"dataset_path": "Idavidrein/gpqa",
"dataset_name": "gpqa_diamond",
"training_split": "train",
"validation_split": "train",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n choices = [\n preprocess(doc[\"Incorrect Answer 1\"]),\n preprocess(doc[\"Incorrect Answer 2\"]),\n preprocess(doc[\"Incorrect Answer 3\"]),\n preprocess(doc[\"Correct Answer\"]),\n ]\n\n random.shuffle(choices)\n correct_answer_index = choices.index(preprocess(doc[\"Correct Answer\"]))\n\n out_doc = {\n \"choice1\": choices[0],\n \"choice2\": choices[1],\n \"choice3\": choices[2],\n \"choice4\": choices[3],\n \"answer\": f\"({chr(65 + correct_answer_index)})\",\n }\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "What is the correct answer to this question:{{Question}}\nChoices:\n(A) {{choice1}}\n(B) {{choice2}}\n(C) {{choice3}}\n(D) {{choice4}}\nAnswer: ",
"doc_to_target": "answer",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"leaderboard_gpqa_extended": {
"task": "leaderboard_gpqa_extended",
"group": "leaderboard_gpqa",
"dataset_path": "Idavidrein/gpqa",
"dataset_name": "gpqa_extended",
"training_split": "train",
"validation_split": "train",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n choices = [\n preprocess(doc[\"Incorrect Answer 1\"]),\n preprocess(doc[\"Incorrect Answer 2\"]),\n preprocess(doc[\"Incorrect Answer 3\"]),\n preprocess(doc[\"Correct Answer\"]),\n ]\n\n random.shuffle(choices)\n correct_answer_index = choices.index(preprocess(doc[\"Correct Answer\"]))\n\n out_doc = {\n \"choice1\": choices[0],\n \"choice2\": choices[1],\n \"choice3\": choices[2],\n \"choice4\": choices[3],\n \"answer\": f\"({chr(65 + correct_answer_index)})\",\n }\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "What is the correct answer to this question:{{Question}}\nChoices:\n(A) {{choice1}}\n(B) {{choice2}}\n(C) {{choice3}}\n(D) {{choice4}}\nAnswer: ",
"doc_to_target": "answer",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"leaderboard_gpqa_main": {
"task": "leaderboard_gpqa_main",
"group": "leaderboard_gpqa",
"dataset_path": "Idavidrein/gpqa",
"dataset_name": "gpqa_main",
"training_split": "train",
"validation_split": "train",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n choices = [\n preprocess(doc[\"Incorrect Answer 1\"]),\n preprocess(doc[\"Incorrect Answer 2\"]),\n preprocess(doc[\"Incorrect Answer 3\"]),\n preprocess(doc[\"Correct Answer\"]),\n ]\n\n random.shuffle(choices)\n correct_answer_index = choices.index(preprocess(doc[\"Correct Answer\"]))\n\n out_doc = {\n \"choice1\": choices[0],\n \"choice2\": choices[1],\n \"choice3\": choices[2],\n \"choice4\": choices[3],\n \"answer\": f\"({chr(65 + correct_answer_index)})\",\n }\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "What is the correct answer to this question:{{Question}}\nChoices:\n(A) {{choice1}}\n(B) {{choice2}}\n(C) {{choice3}}\n(D) {{choice4}}\nAnswer: ",
"doc_to_target": "answer",
"doc_to_choice": [
"(A)",
"(B)",
"(C)",
"(D)"
],
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"leaderboard_ifeval": {
"task": "leaderboard_ifeval",
"group": "leaderboard_instruction_following",
"dataset_path": "wis-k/instruction-following-eval",
"test_split": "train",
"doc_to_text": "prompt",
"doc_to_target": 0,
"process_results": "def process_results(doc, results):\n inp = InputExample(\n key=doc[\"key\"],\n instruction_id_list=doc[\"instruction_id_list\"],\n prompt=doc[\"prompt\"],\n kwargs=doc[\"kwargs\"],\n )\n response = results[0]\n\n out_strict = test_instruction_following_strict(inp, response)\n out_loose = test_instruction_following_loose(inp, response)\n\n return {\n \"prompt_level_strict_acc\": out_strict.follow_all_instructions,\n \"inst_level_strict_acc\": out_strict.follow_instruction_list,\n \"prompt_level_loose_acc\": out_loose.follow_all_instructions,\n \"inst_level_loose_acc\": out_loose.follow_instruction_list,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "prompt_level_strict_acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "inst_level_strict_acc",
"aggregation": "def agg_inst_level_acc(items):\n flat_items = [item for sublist in items for item in sublist]\n inst_level_acc = sum(flat_items) / len(flat_items)\n return inst_level_acc\n",
"higher_is_better": true
},
{
"metric": "prompt_level_loose_acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "inst_level_loose_acc",
"aggregation": "def agg_inst_level_acc(items):\n flat_items = [item for sublist in items for item in sublist]\n inst_level_acc = sum(flat_items) / len(flat_items)\n return inst_level_acc\n",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [],
"do_sample": false,
"temperature": 0.0,
"max_gen_toks": 1280
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 2.0
}
},
"leaderboard_math_algebra_hard": {
"task": "leaderboard_math_algebra_hard",
"group": [
"leaderboard_math_hard"
],
"dataset_path": "lighteval/MATH-Hard",
"dataset_name": "algebra",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x7f50d0552680>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0,
"max_gen_toks": 1024
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"leaderboard_math_counting_and_prob_hard": {
"task": "leaderboard_math_counting_and_prob_hard",
"group": [
"leaderboard_math_hard"
],
"dataset_path": "lighteval/MATH-Hard",
"dataset_name": "counting_and_probability",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x7f50d0580f70>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0,
"max_gen_toks": 1024
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"leaderboard_math_geometry_hard": {
"task": "leaderboard_math_geometry_hard",
"group": [
"leaderboard_math_hard"
],
"dataset_path": "lighteval/MATH-Hard",
"dataset_name": "geometry",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x7f50d1ecf520>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0,
"max_gen_toks": 1024
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"leaderboard_math_intermediate_algebra_hard": {
"task": "leaderboard_math_intermediate_algebra_hard",
"group": [
"leaderboard_math_hard"
],
"dataset_path": "lighteval/MATH-Hard",
"dataset_name": "intermediate_algebra",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x7f50d0583010>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0,
"max_gen_toks": 1024
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"leaderboard_math_num_theory_hard": {
"task": "leaderboard_math_num_theory_hard",
"group": [
"leaderboard_math_hard"
],
"dataset_path": "lighteval/MATH-Hard",
"dataset_name": "number_theory",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x7f50d0550280>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0,
"max_gen_toks": 1024
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"leaderboard_math_prealgebra_hard": {
"task": "leaderboard_math_prealgebra_hard",
"group": [
"leaderboard_math_hard"
],
"dataset_path": "lighteval/MATH-Hard",
"dataset_name": "prealgebra",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x7f50d1e5f7f0>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0,
"max_gen_toks": 1024
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"leaderboard_math_precalculus_hard": {
"task": "leaderboard_math_precalculus_hard",
"group": [
"leaderboard_math_hard"
],
"dataset_path": "lighteval/MATH-Hard",
"dataset_name": "precalculus",
"dataset_kwargs": {
"trust_remote_code": true
},
"training_split": "train",
"test_split": "test",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n",
"doc_to_target": "{{answer if few_shot is undefined else solution}}",
"process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n",
"samples": "<function list_fewshot_samples at 0x7f50d052dea0>"
},
"num_fewshot": 4,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Problem:"
],
"do_sample": false,
"temperature": 0.0,
"max_gen_toks": 1024
},
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"leaderboard_mmlu_pro": {
"task": "leaderboard_mmlu_pro",
"dataset_path": "TIGER-Lab/MMLU-Pro",
"test_split": "test",
"fewshot_split": "validation",
"doc_to_text": "def doc_to_text(doc):\n doc_to_text = f\"{doc['question']}\\n\"\n\n for i in range(len(doc[\"options\"])):\n doc_to_text += f\"{string.ascii_uppercase[i]}. {doc['options'][i]}\\n\"\n\n doc_to_text += \"Answer:\"\n return doc_to_text\n",
"doc_to_target": "answer",
"doc_to_choice": "def doc_to_choice(doc):\n return [string.ascii_uppercase[i] for i in range(len(doc[\"options\"]))]\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 5,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 0.1
}
},
"leaderboard_musr_murder_mysteries": {
"task": "leaderboard_musr_murder_mysteries",
"group": [
"leaderboard_musr"
],
"dataset_path": "TAUR-Lab/MuSR",
"test_split": "murder_mysteries",
"doc_to_text": "def doc_to_text(doc):\n \"\"\"\n Convert a doc to text.\n \"\"\"\n choices = \"\"\n for i, choice in enumerate(ast.literal_eval(doc[\"choices\"])):\n choices += f\"{i+1} - {choice}\\n\"\n\n text = DOC_TO_TEXT.format(\n narrative=doc[\"narrative\"], question=doc[\"question\"], choices=choices\n )\n\n return text\n",
"doc_to_target": "{{answer_choice}}",
"doc_to_choice": "{{choices}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"leaderboard_musr_object_placements": {
"task": "leaderboard_musr_object_placements",
"group": [
"leaderboard_musr"
],
"dataset_path": "TAUR-Lab/MuSR",
"test_split": "object_placements",
"doc_to_text": "def doc_to_text(doc):\n \"\"\"\n Convert a doc to text.\n \"\"\"\n choices = \"\"\n for i, choice in enumerate(ast.literal_eval(doc[\"choices\"])):\n choices += f\"{i+1} - {choice}\\n\"\n\n text = DOC_TO_TEXT.format(\n narrative=doc[\"narrative\"], question=doc[\"question\"], choices=choices\n )\n\n return text\n",
"doc_to_target": "{{answer_choice}}",
"doc_to_choice": "{{choices}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"leaderboard_musr_team_allocation": {
"task": "leaderboard_musr_team_allocation",
"group": [
"leaderboard_musr"
],
"dataset_path": "TAUR-Lab/MuSR",
"test_split": "team_allocation",
"doc_to_text": "def doc_to_text(doc):\n \"\"\"\n Convert a doc to text.\n \"\"\"\n choices = \"\"\n for i, choice in enumerate(ast.literal_eval(doc[\"choices\"])):\n choices += f\"{i+1} - {choice}\\n\"\n\n text = DOC_TO_TEXT.format(\n narrative=doc[\"narrative\"], question=doc[\"question\"], choices=choices\n )\n\n return text\n",
"doc_to_target": "{{answer_choice}}",
"doc_to_choice": "{{choices}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
}
},
"versions": {
"leaderboard_bbh_boolean_expressions": 0.0,
"leaderboard_bbh_causal_judgement": 0.0,
"leaderboard_bbh_date_understanding": 0.0,
"leaderboard_bbh_disambiguation_qa": 0.0,
"leaderboard_bbh_formal_fallacies": 0.0,
"leaderboard_bbh_geometric_shapes": 0.0,
"leaderboard_bbh_hyperbaton": 0.0,
"leaderboard_bbh_logical_deduction_five_objects": 0.0,
"leaderboard_bbh_logical_deduction_seven_objects": 0.0,
"leaderboard_bbh_logical_deduction_three_objects": 0.0,
"leaderboard_bbh_movie_recommendation": 0.0,
"leaderboard_bbh_navigate": 0.0,
"leaderboard_bbh_object_counting": 0.0,
"leaderboard_bbh_penguins_in_a_table": 0.0,
"leaderboard_bbh_reasoning_about_colored_objects": 0.0,
"leaderboard_bbh_ruin_names": 0.0,
"leaderboard_bbh_salient_translation_error_detection": 0.0,
"leaderboard_bbh_snarks": 0.0,
"leaderboard_bbh_sports_understanding": 0.0,
"leaderboard_bbh_temporal_sequences": 0.0,
"leaderboard_bbh_tracking_shuffled_objects_five_objects": 0.0,
"leaderboard_bbh_tracking_shuffled_objects_seven_objects": 0.0,
"leaderboard_bbh_tracking_shuffled_objects_three_objects": 0.0,
"leaderboard_bbh_web_of_lies": 0.0,
"leaderboard_gpqa_diamond": 1.0,
"leaderboard_gpqa_extended": 1.0,
"leaderboard_gpqa_main": 1.0,
"leaderboard_ifeval": 2.0,
"leaderboard_math_algebra_hard": 1.0,
"leaderboard_math_counting_and_prob_hard": 1.0,
"leaderboard_math_geometry_hard": 1.0,
"leaderboard_math_intermediate_algebra_hard": 1.0,
"leaderboard_math_num_theory_hard": 1.0,
"leaderboard_math_prealgebra_hard": 1.0,
"leaderboard_math_precalculus_hard": 1.0,
"leaderboard_mmlu_pro": 0.1,
"leaderboard_musr_murder_mysteries": 1.0,
"leaderboard_musr_object_placements": 1.0,
"leaderboard_musr_team_allocation": 1.0
},
"n-shot": {
"leaderboard": 0,
"leaderboard_bbh": 3,
"leaderboard_bbh_boolean_expressions": 3,
"leaderboard_bbh_causal_judgement": 3,
"leaderboard_bbh_date_understanding": 3,
"leaderboard_bbh_disambiguation_qa": 3,
"leaderboard_bbh_formal_fallacies": 3,
"leaderboard_bbh_geometric_shapes": 3,
"leaderboard_bbh_hyperbaton": 3,
"leaderboard_bbh_logical_deduction_five_objects": 3,
"leaderboard_bbh_logical_deduction_seven_objects": 3,
"leaderboard_bbh_logical_deduction_three_objects": 3,
"leaderboard_bbh_movie_recommendation": 3,
"leaderboard_bbh_navigate": 3,
"leaderboard_bbh_object_counting": 3,
"leaderboard_bbh_penguins_in_a_table": 3,
"leaderboard_bbh_reasoning_about_colored_objects": 3,
"leaderboard_bbh_ruin_names": 3,
"leaderboard_bbh_salient_translation_error_detection": 3,
"leaderboard_bbh_snarks": 3,
"leaderboard_bbh_sports_understanding": 3,
"leaderboard_bbh_temporal_sequences": 3,
"leaderboard_bbh_tracking_shuffled_objects_five_objects": 3,
"leaderboard_bbh_tracking_shuffled_objects_seven_objects": 3,
"leaderboard_bbh_tracking_shuffled_objects_three_objects": 3,
"leaderboard_bbh_web_of_lies": 3,
"leaderboard_gpqa": 0,
"leaderboard_gpqa_diamond": 0,
"leaderboard_gpqa_extended": 0,
"leaderboard_gpqa_main": 0,
"leaderboard_ifeval": 0,
"leaderboard_math_algebra_hard": 4,
"leaderboard_math_counting_and_prob_hard": 4,
"leaderboard_math_geometry_hard": 4,
"leaderboard_math_hard": 4,
"leaderboard_math_intermediate_algebra_hard": 4,
"leaderboard_math_num_theory_hard": 4,
"leaderboard_math_prealgebra_hard": 4,
"leaderboard_math_precalculus_hard": 4,
"leaderboard_mmlu_pro": 5,
"leaderboard_musr": 0,
"leaderboard_musr_murder_mysteries": 0,
"leaderboard_musr_object_placements": 0,
"leaderboard_musr_team_allocation": 0
},
"higher_is_better": {
"leaderboard": {
"acc_norm": true,
"prompt_level_strict_acc": true,
"inst_level_strict_acc": true,
"prompt_level_loose_acc": true,
"inst_level_loose_acc": true,
"exact_match": true,
"acc": true
},
"leaderboard_bbh": {
"acc_norm": true
},
"leaderboard_bbh_boolean_expressions": {
"acc_norm": true
},
"leaderboard_bbh_causal_judgement": {
"acc_norm": true
},
"leaderboard_bbh_date_understanding": {
"acc_norm": true
},
"leaderboard_bbh_disambiguation_qa": {
"acc_norm": true
},
"leaderboard_bbh_formal_fallacies": {
"acc_norm": true
},
"leaderboard_bbh_geometric_shapes": {
"acc_norm": true
},
"leaderboard_bbh_hyperbaton": {
"acc_norm": true
},
"leaderboard_bbh_logical_deduction_five_objects": {
"acc_norm": true
},
"leaderboard_bbh_logical_deduction_seven_objects": {
"acc_norm": true
},
"leaderboard_bbh_logical_deduction_three_objects": {
"acc_norm": true
},
"leaderboard_bbh_movie_recommendation": {
"acc_norm": true
},
"leaderboard_bbh_navigate": {
"acc_norm": true
},
"leaderboard_bbh_object_counting": {
"acc_norm": true
},
"leaderboard_bbh_penguins_in_a_table": {
"acc_norm": true
},
"leaderboard_bbh_reasoning_about_colored_objects": {
"acc_norm": true
},
"leaderboard_bbh_ruin_names": {
"acc_norm": true
},
"leaderboard_bbh_salient_translation_error_detection": {
"acc_norm": true
},
"leaderboard_bbh_snarks": {
"acc_norm": true
},
"leaderboard_bbh_sports_understanding": {
"acc_norm": true
},
"leaderboard_bbh_temporal_sequences": {
"acc_norm": true
},
"leaderboard_bbh_tracking_shuffled_objects_five_objects": {
"acc_norm": true
},
"leaderboard_bbh_tracking_shuffled_objects_seven_objects": {
"acc_norm": true
},
"leaderboard_bbh_tracking_shuffled_objects_three_objects": {
"acc_norm": true
},
"leaderboard_bbh_web_of_lies": {
"acc_norm": true
},
"leaderboard_gpqa": {
"acc_norm": true
},
"leaderboard_gpqa_diamond": {
"acc_norm": true
},
"leaderboard_gpqa_extended": {
"acc_norm": true
},
"leaderboard_gpqa_main": {
"acc_norm": true
},
"leaderboard_ifeval": {
"prompt_level_strict_acc": true,
"inst_level_strict_acc": true,
"prompt_level_loose_acc": true,
"inst_level_loose_acc": true
},
"leaderboard_math_algebra_hard": {
"exact_match": true
},
"leaderboard_math_counting_and_prob_hard": {
"exact_match": true
},
"leaderboard_math_geometry_hard": {
"exact_match": true
},
"leaderboard_math_hard": {
"exact_match": true
},
"leaderboard_math_intermediate_algebra_hard": {
"exact_match": true
},
"leaderboard_math_num_theory_hard": {
"exact_match": true
},
"leaderboard_math_prealgebra_hard": {
"exact_match": true
},
"leaderboard_math_precalculus_hard": {
"exact_match": true
},
"leaderboard_mmlu_pro": {
"acc": true
},
"leaderboard_musr": {
"acc_norm": true
},
"leaderboard_musr_murder_mysteries": {
"acc_norm": true
},
"leaderboard_musr_object_placements": {
"acc_norm": true
},
"leaderboard_musr_team_allocation": {
"acc_norm": true
}
},
"n-samples": {
"leaderboard_musr_murder_mysteries": {
"original": 250,
"effective": 250
},
"leaderboard_musr_team_allocation": {
"original": 250,
"effective": 250
},
"leaderboard_musr_object_placements": {
"original": 256,
"effective": 256
},
"leaderboard_ifeval": {
"original": 541,
"effective": 541
},
"leaderboard_math_intermediate_algebra_hard": {
"original": 280,
"effective": 280
},
"leaderboard_math_counting_and_prob_hard": {
"original": 123,
"effective": 123
},
"leaderboard_math_algebra_hard": {
"original": 307,
"effective": 307
},
"leaderboard_math_num_theory_hard": {
"original": 154,
"effective": 154
},
"leaderboard_math_precalculus_hard": {
"original": 135,
"effective": 135
},
"leaderboard_math_geometry_hard": {
"original": 132,
"effective": 132
},
"leaderboard_math_prealgebra_hard": {
"original": 193,
"effective": 193
},
"leaderboard_gpqa_main": {
"original": 448,
"effective": 448
},
"leaderboard_gpqa_extended": {
"original": 546,
"effective": 546
},
"leaderboard_gpqa_diamond": {
"original": 198,
"effective": 198
},
"leaderboard_bbh_sports_understanding": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_object_counting": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_geometric_shapes": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_hyperbaton": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_disambiguation_qa": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_logical_deduction_three_objects": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_causal_judgement": {
"original": 187,
"effective": 187
},
"leaderboard_bbh_tracking_shuffled_objects_seven_objects": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_temporal_sequences": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_web_of_lies": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_formal_fallacies": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_salient_translation_error_detection": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_tracking_shuffled_objects_five_objects": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_ruin_names": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_logical_deduction_five_objects": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_penguins_in_a_table": {
"original": 146,
"effective": 146
},
"leaderboard_bbh_movie_recommendation": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_snarks": {
"original": 178,
"effective": 178
},
"leaderboard_bbh_boolean_expressions": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_navigate": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_date_understanding": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_reasoning_about_colored_objects": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_logical_deduction_seven_objects": {
"original": 250,
"effective": 250
},
"leaderboard_bbh_tracking_shuffled_objects_three_objects": {
"original": 250,
"effective": 250
},
"leaderboard_mmlu_pro": {
"original": 12032,
"effective": 12032
}
},
"config": {
"model": "hf",
"model_args": "pretrained=Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base,revision=f1e2cad4dca10f948fd2ee9588f80df0b40d7232,trust_remote_code=False,dtype=bfloat16,parallelize=False",
"model_num_parameters": 8030261248,
"model_dtype": "torch.bfloat16",
"model_revision": "f1e2cad4dca10f948fd2ee9588f80df0b40d7232",
"model_sha": "f1e2cad4dca10f948fd2ee9588f80df0b40d7232",
"batch_size": "auto",
"batch_sizes": [
8
],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "9694c56",
"date": 1727924738.0324128,
"pretty_env_info": "PyTorch version: 2.3.1+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 20.04.6 LTS (x86_64)\nGCC version: (Ubuntu 10.5.0-1ubuntu1~20.04) 10.5.0\nClang version: Could not collect\nCMake version: version 3.27.7\nLibc version: glibc-2.31\n\nPython version: 3.10.14 (main, May 6 2024, 19:42:50) [GCC 11.2.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1048-aws-x86_64-with-glibc2.31\nIs CUDA available: True\nCUDA runtime version: 12.1.105\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA H100 80GB HBM3\nGPU 1: NVIDIA H100 80GB HBM3\nGPU 2: NVIDIA H100 80GB HBM3\nGPU 3: NVIDIA H100 80GB HBM3\nGPU 4: NVIDIA H100 80GB HBM3\nGPU 5: NVIDIA H100 80GB HBM3\nGPU 6: NVIDIA H100 80GB HBM3\nGPU 7: NVIDIA H100 80GB HBM3\n\nNvidia driver version: 535.104.12\ncuDNN version: Could not collect\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nByte Order: Little Endian\nAddress sizes: 48 bits physical, 48 bits virtual\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nNUMA node(s): 2\nVendor ID: AuthenticAMD\nCPU family: 25\nModel: 1\nModel name: AMD EPYC 7R13 Processor\nStepping: 1\nCPU MHz: 2650.000\nBogoMIPS: 5300.00\nHypervisor vendor: KVM\nVirtualization type: full\nL1d cache: 3 MiB\nL1i cache: 3 MiB\nL2 cache: 48 MiB\nL3 cache: 384 MiB\nNUMA node0 CPU(s): 0-47\nNUMA node1 CPU(s): 48-95\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch topoext perfctr_core invpcid_single ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru wbnoinvd arat npt nrip_save vaes vpclmulqdq rdpid\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] torch==2.3.1\n[pip3] triton==2.3.1\n[conda] numpy 1.26.4 pypi_0 pypi\n[conda] torch 2.3.1 pypi_0 pypi\n[conda] triton 2.3.1 pypi_0 pypi",
"transformers_version": "4.45.1",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<|eot_id|>",
"128009"
],
"tokenizer_eos_token": [
"<|eot_id|>",
"128009"
],
"tokenizer_bos_token": [
"<|begin_of_text|>",
"128000"
],
"eot_token_id": 128009,
"max_length": 131072,
"task_hashes": {
"leaderboard_musr_murder_mysteries": "82e5c06e6cd792fb4b45037299b70f1fbcdecc78edc4f795aac434685f176f0a",
"leaderboard_musr_team_allocation": "eecbf3fd31c82a952ccb699ab0bf397b3cb7472ee7dd0c2ddb5a3d4126f5cc4d",
"leaderboard_musr_object_placements": "4309049f933e4c7824831951197d0f1c5c31478f44b2b83340cf5a3d1cd94252",
"leaderboard_ifeval": "2837c2ef7db9e17f4c8855ee8a23fb7b542ac98a182c6a58fc0b0fcd9945879c",
"leaderboard_math_intermediate_algebra_hard": "598c58b5a46617c55018d9b6bde89346789c4e502457b87b556b445d0e7a82b5",
"leaderboard_math_counting_and_prob_hard": "6a4e19e8df829d113d0440706a20920262e57de707b8488019ad9656e9eb6313",
"leaderboard_math_algebra_hard": "16d51a0d20a8554a9631cf94ca496b279c46875fab49770ff20c3b8f3a8ba0ae",
"leaderboard_math_num_theory_hard": "a222ceb13607cf9ba52cdc2e8e835c052b86ccca7ef982095b9ab768437433c2",
"leaderboard_math_precalculus_hard": "91ca5e4eb93f261586596a5578a042641920b114cef8d424fda4e3b4d5c0cb3f",
"leaderboard_math_geometry_hard": "7302265920690ce81983baa029accd4b812780f55d1c92ead9f305772fa15612",
"leaderboard_math_prealgebra_hard": "f8a84825698d4a1fb4ff7f3f3873f3b5301d80b1230f7e59d2c59330da54cfd8",
"leaderboard_gpqa_main": "dafcb9d9a201db36e4da08c3eb9d5b8679800ec529dc0a2ecd2389e16144b701",
"leaderboard_gpqa_extended": "1b26fb979e17c1e0176fa3fc95320fba19d8c45d7e5a881459928ba118c277c9",
"leaderboard_gpqa_diamond": "5cbe0a6730301be85b0ec6ae4bfa9a9bf08a764d88c52b08c02f6da5f4b1e37d",
"leaderboard_bbh_sports_understanding": "026370544306c9acef2ef7ccc95807ccfd820bb1e83cba02e84a725d4b0ebd70",
"leaderboard_bbh_object_counting": "88b1291daeeab0df474d0f251b8db44e50940a5f23cdded438c538fd9ec0e883",
"leaderboard_bbh_geometric_shapes": "3cd8a233ea75aac02ff81ba79fcead1c7da6d53d50938d2c0d51e35736dda4b1",
"leaderboard_bbh_hyperbaton": "02bbd19d1fa28d4697c7159f41e1471bb516fccb1e7be3126aa96afc187bc49c",
"leaderboard_bbh_disambiguation_qa": "f37e873f7dc567fec731fed4a638c65189509ecce3dcea9000a0c020e0983649",
"leaderboard_bbh_logical_deduction_three_objects": "32c1b62081a255c56fef12d2568c5c9eafa5083a997d34ee21ee3d9a1de1fff5",
"leaderboard_bbh_causal_judgement": "1c732598c4b1c09aba67601b3a8003ffb099e5e7d8f52c177a9506d0532f45b6",
"leaderboard_bbh_tracking_shuffled_objects_seven_objects": "11c6c23d203396c493b314febfd2d534f32547951ad909c0defe9ea82e7a502f",
"leaderboard_bbh_temporal_sequences": "0e525a2f05b9fe40dc5357ed12307d59a25dbb4bc842458eedcdba4b5c9eb857",
"leaderboard_bbh_web_of_lies": "45dcaa80145efb2a1f934c9eaeaeb4664db82f1f76ec4ee1cc14e89a1fac751f",
"leaderboard_bbh_formal_fallacies": "b1e118530a16c5539fb8c3e218d85fc1219929b312b84392c3079c86cd9ccc76",
"leaderboard_bbh_salient_translation_error_detection": "6267af09b70849a722b147df5af5ead66ac3e13f94414f25dfd851e8b750d6d6",
"leaderboard_bbh_tracking_shuffled_objects_five_objects": "67e10d8183354ae10982a5aa890bd149459d93ac691936e95c8a6c24f9f5c695",
"leaderboard_bbh_ruin_names": "fc196e10fe029c470f444d0f48cb55d7f3489211b21fe5926a4fd681da6e9015",
"leaderboard_bbh_logical_deduction_five_objects": "6ea7e06fff520b5bba3ed25885a3f9491b468f61686072e50b304527daea30a4",
"leaderboard_bbh_penguins_in_a_table": "b03b17b0a215b1a963d70797dae05bfac8f23cdc79564e3f4b8d13a28d529b8a",
"leaderboard_bbh_movie_recommendation": "4d1c170a449a802f9255f433a998130e1fa23b4fb315cf34edffc824e1377aa8",
"leaderboard_bbh_snarks": "5a6a4dcecdfe221aa94366007ea93ecaa722b0b7f67b9a416df361ee041bc302",
"leaderboard_bbh_boolean_expressions": "f05094b6e8bce171b0ec6aca22f7cffb8475628ece23ae4548b2f3a5e3034faf",
"leaderboard_bbh_navigate": "015befb52999093693473ff3da9a992605e0e1415e31d32addf4584b3d4d2da4",
"leaderboard_bbh_date_understanding": "13cce2ae9814f84c4f43e0dc4c1749bb31ba727eff09f9e283eb6d1131387e51",
"leaderboard_bbh_reasoning_about_colored_objects": "9d770f2a987d7d3659ecda9aeb915e41571e76e1a1907d374383801046c02c0d",
"leaderboard_bbh_logical_deduction_seven_objects": "045a50e3815b22fe80e1949f2326555ed283b0693f97b2334118e079a7f2531f",
"leaderboard_bbh_tracking_shuffled_objects_three_objects": "a660532e863ae405ac3cb09b3595987065aed1f972d2de372780b27db2b7a326",
"leaderboard_mmlu_pro": "01bda4c4d715f0aad6227ad2370a430cb76ecfee349b63f23b2060195dc7dd3e"
},
"model_source": "hf",
"model_name": "Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base",
"model_name_sanitized": "Joseph717171__Llama-3.1-SuperNova-8B-Lite_TIES_with_Base",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": true,
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
"chat_template_sha": "b48c47f6443892716176eb200bf4ef108f64e06ca26ed0fa8ebc0a4b3992fcb2",
"start_time": 833784.813733483,
"end_time": 835869.051408136,
"total_evaluation_time_seconds": "2084.2376746530645"
} |