Benchmark Run Details

Run Summary

Model gemma3:4b:Q4_K_M
Benchmark 0015_spell_check
Normed Score 74
Run Timestamp 2025-03-26 18:30:08

Question-Level Details

Question ID Score Evaluation Time (ms) Debug Info
0015_spell_check:attention:0 0 1659 { "response": { "incorrect": "atteton", "correct": "attention" }, "expected": { "incorrect": "attetion", "correct": "attention" } }
[+]
0015_spell_check:attention:1 100 883 { "response": { "incorrect": "attantion", "correct": "attention" }, "expected": { "incorrect": "attantion", "correct": "attention" } }
[+]
0015_spell_check:attention:2 100 658 { "response": { "incorrect": "attetion", "correct": "attention" }, "expected": { "incorrect": "attetion", "correct": "attention" } }
[+]
0015_spell_check:attention:3 100 1187 { "response": { "incorrect": "attnetion", "correct": "attention" }, "expected": { "incorrect": "attnetion", "correct": "attention" } }
[+]
0015_spell_check:attention:4 100 1817 { "response": { "incorrect": "attntion", "correct": "attention" }, "expected": { "incorrect": "attntion", "correct": "attention" } }
[+]
0015_spell_check:attention:5 100 1088 { "response": { "incorrect": "attenion", "correct": "attention" }, "expected": { "incorrect": "attenion", "correct": "attention" } }
[+]
0015_spell_check:attention:6 100 862 { "response": { "incorrect": "attenion", "correct": "attention" }, "expected": { "incorrect": "attenion", "correct": "attention" } }
[+]
0015_spell_check:attention:7 0 972 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "attetion", "correct": "attention" } }
[+]
0015_spell_check:attention:8 100 1297 { "response": { "incorrect": "atttention", "correct": "attention" }, "expected": { "incorrect": "atttention", "correct": "attention" } }
[+]
0015_spell_check:attention:9 100 1595 { "response": { "incorrect": "attenttion", "correct": "attention" }, "expected": { "incorrect": "attenttion", "correct": "attention" } }
[+]
0015_spell_check:demonstrate:0 100 1069 { "response": { "incorrect": "demonstraite", "correct": "demonstrate" }, "expected": { "incorrect": "demonstraite", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:1 100 903 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:2 100 911 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:3 100 989 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:4 100 965 { "response": { "incorrect": "demanstrate", "correct": "demonstrate" }, "expected": { "incorrect": "demanstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:5 100 928 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:6 100 1271 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:7 100 1015 { "response": { "incorrect": "demonstarte", "correct": "demonstrate" }, "expected": { "incorrect": "demonstarte", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:8 100 931 { "response": { "incorrect": "deomstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:9 100 1251 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:laboratory:0 0 968 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:1 0 936 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:2 0 881 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:3 0 868 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:4 0 967 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:5 100 916 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:6 0 883 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:7 100 1263 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:8 100 1261 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:9 100 1237 { "response": { "incorrect": "laberatory", "correct": "laboratory" }, "expected": { "incorrect": "laberatory", "correct": "laboratory" } }
[+]
0015_spell_check:laughter:0 0 1311 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "laughterr", "correct": "laughter" } }
[+]
0015_spell_check:laughter:1 100 856 { "response": { "incorrect": "laghter", "correct": "laughter" }, "expected": { "incorrect": "laghter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:2 100 877 { "response": { "incorrect": "laghter", "correct": "laughter" }, "expected": { "incorrect": "laghter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:3 100 940 { "response": { "incorrect": "laghter", "correct": "laughter" }, "expected": { "incorrect": "laghter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:4 100 879 { "response": { "incorrect": "lafter", "correct": "laughter" }, "expected": { "incorrect": "lafter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:5 100 1196 { "response": { "incorrect": "laghter", "correct": "laughter" }, "expected": { "incorrect": "laghter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:6 100 887 { "response": { "incorrect": "laugther", "correct": "laughter" }, "expected": { "incorrect": "laugther", "correct": "laughter" } }
[+]
0015_spell_check:laughter:7 100 903 { "response": { "incorrect": "laughtter", "correct": "laughter" }, "expected": { "incorrect": "laughtter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:8 100 1185 { "response": { "incorrect": "laughtur", "correct": "laughter" }, "expected": { "incorrect": "laughtur", "correct": "laughter" } }
[+]
0015_spell_check:laughter:9 100 910 { "response": { "incorrect": "laugther", "correct": "laughter" }, "expected": { "incorrect": "laugther", "correct": "laughter" } }
[+]
0015_spell_check:liaison:0 0 887 { "response": { "incorrect": "liaison", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:1 100 1567 { "response": { "incorrect": "liason", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:2 0 992 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "liasion", "correct": "liaison" } }
[+]
0015_spell_check:liaison:3 100 1197 { "response": { "incorrect": "liason", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:4 0 890 { "response": { "incorrect": "liaison", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:5 0 1314 { "response": { "incorrect": "liaison", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:6 0 1198 { "response": { "incorrect": "liaison", "correct": "liaison" }, "expected": { "incorrect": "liasion", "correct": "liaison" } }
[+]
0015_spell_check:liaison:7 0 1219 { "response": { "incorrect": "leason", "correct": "lesson" }, "expected": { "incorrect": "leason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:8 0 1221 { "response": { "incorrect": "liaison", "correct": "liaison" }, "expected": { "incorrect": "liasion", "correct": "liaison" } }
[+]
0015_spell_check:liaison:9 0 910 { "response": { "incorrect": "liaison", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:orange:0 100 1198 { "response": { "incorrect": "orrange", "correct": "orange" }, "expected": { "incorrect": "orrange", "correct": "orange" } }
[+]
0015_spell_check:orange:1 0 789 { "response": { "incorrect": "orange", "correct": "orange" }, "expected": { "incorrect": "oranje", "correct": "orange" } }
[+]
0015_spell_check:orange:2 100 789 { "response": { "incorrect": "orang", "correct": "orange" }, "expected": { "incorrect": "orang", "correct": "orange" } }
[+]
0015_spell_check:orange:3 100 1222 { "response": { "incorrect": "oranage", "correct": "orange" }, "expected": { "incorrect": "oranage", "correct": "orange" } }
[+]
0015_spell_check:orange:4 100 1163 { "response": { "incorrect": "oranage", "correct": "orange" }, "expected": { "incorrect": "oranage", "correct": "orange" } }
[+]
0015_spell_check:orange:5 0 802 { "response": { "incorrect": "orange", "correct": "orange" }, "expected": { "incorrect": "orrange", "correct": "orange" } }
[+]
0015_spell_check:orange:6 100 1184 { "response": { "incorrect": "orrange", "correct": "orange" }, "expected": { "incorrect": "orrange", "correct": "orange" } }
[+]
0015_spell_check:orange:7 100 1199 { "response": { "incorrect": "oringe", "correct": "orange" }, "expected": { "incorrect": "oringe", "correct": "orange" } }
[+]
0015_spell_check:orange:8 100 1189 { "response": { "incorrect": "orennge", "correct": "orange" }, "expected": { "incorrect": "orennge", "correct": "orange" } }
[+]
0015_spell_check:orange:9 100 1170 { "response": { "incorrect": "orrange", "correct": "orange" }, "expected": { "incorrect": "orrange", "correct": "orange" } }
[+]
0015_spell_check:partition:0 0 901 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "partioned", "correct": "partitioned" } }
[+]
0015_spell_check:partition:1 100 1168 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:2 100 863 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:3 100 1248 { "response": { "incorrect": "partionned", "correct": "partitioned" }, "expected": { "incorrect": "partionned", "correct": "partitioned" } }
[+]
0015_spell_check:partition:4 100 868 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:5 0 848 { "response": { "incorrect": "partion", "correct": "portion" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:6 100 832 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:7 100 843 { "response": { "incorrect": "particion", "correct": "partition" }, "expected": { "incorrect": "particion", "correct": "partition" } }
[+]
0015_spell_check:partition:8 100 1176 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:9 100 915 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:party:0 100 1099 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:1 100 842 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:2 100 1192 { "response": { "incorrect": "pary", "correct": "party" }, "expected": { "incorrect": "pary", "correct": "party" } }
[+]
0015_spell_check:party:3 100 858 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:4 100 845 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:5 100 808 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:6 100 817 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:7 100 1186 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:8 100 1199 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:9 100 838 { "response": { "incorrect": "pary", "correct": "party" }, "expected": { "incorrect": "pary", "correct": "party" } }
[+]
0015_spell_check:stable:0 100 1161 { "response": { "incorrect": "staable", "correct": "stable" }, "expected": { "incorrect": "staable", "correct": "stable" } }
[+]
0015_spell_check:stable:1 100 890 { "response": { "incorrect": "stabe", "correct": "stable" }, "expected": { "incorrect": "stabe", "correct": "stable" } }
[+]
0015_spell_check:stable:2 100 1242 { "response": { "incorrect": "stabal", "correct": "stable" }, "expected": { "incorrect": "stabal", "correct": "stable" } }
[+]
0015_spell_check:stable:3 100 1141 { "response": { "incorrect": "staible", "correct": "stable" }, "expected": { "incorrect": "staible", "correct": "stable" } }
[+]
0015_spell_check:stable:4 100 851 { "response": { "incorrect": "stabel", "correct": "stable" }, "expected": { "incorrect": "stabel", "correct": "stable" } }
[+]
0015_spell_check:stable:5 100 1172 { "response": { "incorrect": "staible", "correct": "stable" }, "expected": { "incorrect": "staible", "correct": "stable" } }
[+]
0015_spell_check:stable:6 100 1218 { "response": { "incorrect": "stabl", "correct": "stable" }, "expected": { "incorrect": "stabl", "correct": "stable" } }
[+]
0015_spell_check:stable:7 100 1150 { "response": { "incorrect": "stabe", "correct": "stable" }, "expected": { "incorrect": "stabe", "correct": "stable" } }
[+]
0015_spell_check:stable:8 100 833 { "response": { "incorrect": "stabble", "correct": "stable" }, "expected": { "incorrect": "stabble", "correct": "stable" } }
[+]
0015_spell_check:stable:9 100 850 { "response": { "incorrect": "stayble", "correct": "stable" }, "expected": { "incorrect": "stayble", "correct": "stable" } }
[+]
0015_spell_check:table:0 100 844 { "response": { "incorrect": "tabele", "correct": "table" }, "expected": { "incorrect": "tabele", "correct": "table" } }
[+]
0015_spell_check:table:1 100 1149 { "response": { "incorrect": "tabble", "correct": "table" }, "expected": { "incorrect": "tabble", "correct": "table" } }
[+]
0015_spell_check:table:2 0 895 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "tabel", "correct": "table" } }
[+]
0015_spell_check:table:3 0 887 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "tabble", "correct": "table" } }
[+]
0015_spell_check:table:4 100 838 { "response": { "incorrect": "tabble", "correct": "table" }, "expected": { "incorrect": "tabble", "correct": "table" } }
[+]
0015_spell_check:table:5 0 878 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "tabl", "correct": "table" } }
[+]
0015_spell_check:table:6 100 836 { "response": { "incorrect": "tabl", "correct": "table" }, "expected": { "incorrect": "tabl", "correct": "table" } }
[+]
0015_spell_check:table:7 100 1166 { "response": { "incorrect": "tabel", "correct": "table" }, "expected": { "incorrect": "tabel", "correct": "table" } }
[+]
0015_spell_check:table:8 0 967 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "tabel", "correct": "table" } }
[+]
0015_spell_check:table:9 0 852 { "response": { "incorrect": "spelled", "correct": "spelled" }, "expected": { "incorrect": "tabel", "correct": "table" } }
[+]