Benchmark Run Details

Run Summary

Model phi4:14b:Q4_K_M
Benchmark 0015_spell_check
Normed Score 98
Run Timestamp 2025-03-26 18:28:22

Question-Level Details

Question ID Score Evaluation Time (ms) Debug Info
0015_spell_check:attention:0 100 9993 { "response": { "incorrect": "attetion", "correct": "attention" }, "expected": { "incorrect": "attetion", "correct": "attention" } }
[+]
0015_spell_check:attention:1 100 2241 { "response": { "incorrect": "attantion", "correct": "attention" }, "expected": { "incorrect": "attantion", "correct": "attention" } }
[+]
0015_spell_check:attention:2 100 2600 { "response": { "incorrect": "attetion", "correct": "attention" }, "expected": { "incorrect": "attetion", "correct": "attention" } }
[+]
0015_spell_check:attention:3 100 4084 { "response": { "incorrect": "attnetion", "correct": "attention" }, "expected": { "incorrect": "attnetion", "correct": "attention" } }
[+]
0015_spell_check:attention:4 100 3728 { "response": { "incorrect": "attntion", "correct": "attention" }, "expected": { "incorrect": "attntion", "correct": "attention" } }
[+]
0015_spell_check:attention:5 100 3407 { "response": { "incorrect": "attenion", "correct": "attention" }, "expected": { "incorrect": "attenion", "correct": "attention" } }
[+]
0015_spell_check:attention:6 100 3476 { "response": { "incorrect": "attenion", "correct": "attention" }, "expected": { "incorrect": "attenion", "correct": "attention" } }
[+]
0015_spell_check:attention:7 100 3484 { "response": { "incorrect": "attetion", "correct": "attention" }, "expected": { "incorrect": "attetion", "correct": "attention" } }
[+]
0015_spell_check:attention:8 100 3540 { "response": { "incorrect": "atttention", "correct": "attention" }, "expected": { "incorrect": "atttention", "correct": "attention" } }
[+]
0015_spell_check:attention:9 100 3628 { "response": { "incorrect": "attenttion", "correct": "attention" }, "expected": { "incorrect": "attenttion", "correct": "attention" } }
[+]
0015_spell_check:demonstrate:0 100 4200 { "response": { "incorrect": "demonstraite", "correct": "demonstrate" }, "expected": { "incorrect": "demonstraite", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:1 100 4099 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:2 100 4155 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:3 100 4715 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:4 100 3994 { "response": { "incorrect": "demanstrate", "correct": "demonstrate" }, "expected": { "incorrect": "demanstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:5 100 3963 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:6 100 4245 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:7 100 4516 { "response": { "incorrect": "demonstarte", "correct": "demonstrate" }, "expected": { "incorrect": "demonstarte", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:8 100 3801 { "response": { "incorrect": "deomstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:9 100 3775 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:laboratory:0 100 3746 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:1 100 3737 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:2 100 3702 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:3 100 3665 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:4 100 3655 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:5 100 3705 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:6 100 3772 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:7 100 3646 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:8 100 3620 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:9 100 3615 { "response": { "incorrect": "laberatory", "correct": "laboratory" }, "expected": { "incorrect": "laberatory", "correct": "laboratory" } }
[+]
0015_spell_check:laughter:0 100 3771 { "response": { "incorrect": "laughterr", "correct": "laughter" }, "expected": { "incorrect": "laughterr", "correct": "laughter" } }
[+]
0015_spell_check:laughter:1 100 3638 { "response": { "incorrect": "laghter", "correct": "laughter" }, "expected": { "incorrect": "laghter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:2 100 3493 { "response": { "incorrect": "laghter", "correct": "laughter" }, "expected": { "incorrect": "laghter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:3 100 3520 { "response": { "incorrect": "laghter", "correct": "laughter" }, "expected": { "incorrect": "laghter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:4 100 3246 { "response": { "incorrect": "lafter", "correct": "laughter" }, "expected": { "incorrect": "lafter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:5 100 4251 { "response": { "incorrect": "laghter", "correct": "laughter" }, "expected": { "incorrect": "laghter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:6 100 3344 { "response": { "incorrect": "laugther", "correct": "laughter" }, "expected": { "incorrect": "laugther", "correct": "laughter" } }
[+]
0015_spell_check:laughter:7 100 3701 { "response": { "incorrect": "laughtter", "correct": "laughter" }, "expected": { "incorrect": "laughtter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:8 100 3330 { "response": { "incorrect": "laughtur", "correct": "laughter" }, "expected": { "incorrect": "laughtur", "correct": "laughter" } }
[+]
0015_spell_check:laughter:9 100 3224 { "response": { "incorrect": "laugther", "correct": "laughter" }, "expected": { "incorrect": "laugther", "correct": "laughter" } }
[+]
0015_spell_check:liaison:0 100 3341 { "response": { "incorrect": "liason", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:1 100 3135 { "response": { "incorrect": "liason", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:2 100 3119 { "response": { "incorrect": "liasion", "correct": "liaison" }, "expected": { "incorrect": "liasion", "correct": "liaison" } }
[+]
0015_spell_check:liaison:3 100 3228 { "response": { "incorrect": "liason", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:4 100 3164 { "response": { "incorrect": "liason", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:5 100 3043 { "response": { "incorrect": "liason", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:6 100 3036 { "response": { "incorrect": "liasion", "correct": "liaison" }, "expected": { "incorrect": "liasion", "correct": "liaison" } }
[+]
0015_spell_check:liaison:7 100 3057 { "response": { "incorrect": "leason", "correct": "liaison" }, "expected": { "incorrect": "leason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:8 100 2985 { "response": { "incorrect": "liasion", "correct": "liaison" }, "expected": { "incorrect": "liasion", "correct": "liaison" } }
[+]
0015_spell_check:liaison:9 100 3362 { "response": { "incorrect": "liason", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:orange:0 100 2804 { "response": { "incorrect": "orrange", "correct": "orange" }, "expected": { "incorrect": "orrange", "correct": "orange" } }
[+]
0015_spell_check:orange:1 100 2856 { "response": { "incorrect": "oranje", "correct": "orange" }, "expected": { "incorrect": "oranje", "correct": "orange" } }
[+]
0015_spell_check:orange:2 100 2707 { "response": { "incorrect": "orang", "correct": "orange" }, "expected": { "incorrect": "orang", "correct": "orange" } }
[+]
0015_spell_check:orange:3 100 2914 { "response": { "incorrect": "oranage", "correct": "orange" }, "expected": { "incorrect": "oranage", "correct": "orange" } }
[+]
0015_spell_check:orange:4 100 3229 { "response": { "incorrect": "oranage", "correct": "orange" }, "expected": { "incorrect": "oranage", "correct": "orange" } }
[+]
0015_spell_check:orange:5 100 2976 { "response": { "incorrect": "orrange", "correct": "orange" }, "expected": { "incorrect": "orrange", "correct": "orange" } }
[+]
0015_spell_check:orange:6 100 2877 { "response": { "incorrect": "orrange", "correct": "orange" }, "expected": { "incorrect": "orrange", "correct": "orange" } }
[+]
0015_spell_check:orange:7 0 2934 { "response": { "incorrect": "orange", "correct": "oranges" }, "expected": { "incorrect": "oringe", "correct": "orange" } }
[+]
0015_spell_check:orange:8 100 2906 { "response": { "incorrect": "orennge", "correct": "orange" }, "expected": { "incorrect": "orennge", "correct": "orange" } }
[+]
0015_spell_check:orange:9 100 2928 { "response": { "incorrect": "orrange", "correct": "orange" }, "expected": { "incorrect": "orrange", "correct": "orange" } }
[+]
0015_spell_check:partition:0 100 3479 { "response": { "incorrect": "partioned", "correct": "partitioned" }, "expected": { "incorrect": "partioned", "correct": "partitioned" } }
[+]
0015_spell_check:partition:1 100 2931 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:2 100 3012 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:3 100 3296 { "response": { "incorrect": "partionned", "correct": "partitioned" }, "expected": { "incorrect": "partionned", "correct": "partitioned" } }
[+]
0015_spell_check:partition:4 100 2975 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:5 100 3118 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:6 100 3001 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:7 100 3059 { "response": { "incorrect": "particion", "correct": "partition" }, "expected": { "incorrect": "particion", "correct": "partition" } }
[+]
0015_spell_check:partition:8 100 3067 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:9 100 3101 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:party:0 100 3084 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:1 100 3134 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:2 100 3171 { "response": { "incorrect": "pary", "correct": "party" }, "expected": { "incorrect": "pary", "correct": "party" } }
[+]
0015_spell_check:party:3 100 3121 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:4 100 3639 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:5 100 3128 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:6 100 3199 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:7 100 3140 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:8 100 3160 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:9 100 3190 { "response": { "incorrect": "pary", "correct": "party" }, "expected": { "incorrect": "pary", "correct": "party" } }
[+]
0015_spell_check:stable:0 100 3213 { "response": { "incorrect": "staable", "correct": "stable" }, "expected": { "incorrect": "staable", "correct": "stable" } }
[+]
0015_spell_check:stable:1 100 3233 { "response": { "incorrect": "stabe", "correct": "stable" }, "expected": { "incorrect": "stabe", "correct": "stable" } }
[+]
0015_spell_check:stable:2 100 3246 { "response": { "incorrect": "stabal", "correct": "stable" }, "expected": { "incorrect": "stabal", "correct": "stable" } }
[+]
0015_spell_check:stable:3 100 3214 { "response": { "incorrect": "staible", "correct": "stable" }, "expected": { "incorrect": "staible", "correct": "stable" } }
[+]
0015_spell_check:stable:4 100 3196 { "response": { "incorrect": "stabel", "correct": "stable" }, "expected": { "incorrect": "stabel", "correct": "stable" } }
[+]
0015_spell_check:stable:5 100 3217 { "response": { "incorrect": "staible", "correct": "stable" }, "expected": { "incorrect": "staible", "correct": "stable" } }
[+]
0015_spell_check:stable:6 100 3207 { "response": { "incorrect": "stabl", "correct": "stable" }, "expected": { "incorrect": "stabl", "correct": "stable" } }
[+]
0015_spell_check:stable:7 100 3191 { "response": { "incorrect": "stabe", "correct": "stable" }, "expected": { "incorrect": "stabe", "correct": "stable" } }
[+]
0015_spell_check:stable:8 100 3191 { "response": { "incorrect": "stabble", "correct": "stable" }, "expected": { "incorrect": "stabble", "correct": "stable" } }
[+]
0015_spell_check:stable:9 0 3196 { "response": { "incorrect": "stabile", "correct": "stable" }, "expected": { "incorrect": "stayble", "correct": "stable" } }
[+]
0015_spell_check:table:0 100 3205 { "response": { "incorrect": "tabele", "correct": "table" }, "expected": { "incorrect": "tabele", "correct": "table" } }
[+]
0015_spell_check:table:1 100 3261 { "response": { "incorrect": "tabble", "correct": "table" }, "expected": { "incorrect": "tabble", "correct": "table" } }
[+]
0015_spell_check:table:2 100 3199 { "response": { "incorrect": "tabel", "correct": "table" }, "expected": { "incorrect": "tabel", "correct": "table" } }
[+]
0015_spell_check:table:3 100 3235 { "response": { "incorrect": "tabble", "correct": "table" }, "expected": { "incorrect": "tabble", "correct": "table" } }
[+]
0015_spell_check:table:4 100 4002 { "response": { "incorrect": "tabble", "correct": "table" }, "expected": { "incorrect": "tabble", "correct": "table" } }
[+]
0015_spell_check:table:5 100 3780 { "response": { "incorrect": "tabl", "correct": "table" }, "expected": { "incorrect": "tabl", "correct": "table" } }
[+]
0015_spell_check:table:6 100 3592 { "response": { "incorrect": "tabl", "correct": "table" }, "expected": { "incorrect": "tabl", "correct": "table" } }
[+]
0015_spell_check:table:7 100 3168 { "response": { "incorrect": "tabel", "correct": "table" }, "expected": { "incorrect": "tabel", "correct": "table" } }
[+]
0015_spell_check:table:8 100 3341 { "response": { "incorrect": "tabel", "correct": "table" }, "expected": { "incorrect": "tabel", "correct": "table" } }
[+]
0015_spell_check:table:9 100 3853 { "response": { "incorrect": "tabel", "correct": "table" }, "expected": { "incorrect": "tabel", "correct": "table" } }
[+]