Benchmark Run Details

Run Summary

Model gemma3:1b:Q4_K_M
Benchmark 0015_spell_check
Normed Score 69
Run Timestamp 2025-03-26 18:30:51

Question-Level Details

Question ID Score Evaluation Time (ms) Debug Info
0015_spell_check:attention:0 100 769 { "response": { "incorrect": "attetion", "correct": "attention" }, "expected": { "incorrect": "attetion", "correct": "attention" } }
[+]
0015_spell_check:attention:1 100 363 { "response": { "incorrect": "attantion", "correct": "attention" }, "expected": { "incorrect": "attantion", "correct": "attention" } }
[+]
0015_spell_check:attention:2 100 357 { "response": { "incorrect": "attetion", "correct": "attention" }, "expected": { "incorrect": "attetion", "correct": "attention" } }
[+]
0015_spell_check:attention:3 100 359 { "response": { "incorrect": "attnetion", "correct": "attention" }, "expected": { "incorrect": "attnetion", "correct": "attention" } }
[+]
0015_spell_check:attention:4 100 363 { "response": { "incorrect": "attntion", "correct": "attention" }, "expected": { "incorrect": "attntion", "correct": "attention" } }
[+]
0015_spell_check:attention:5 0 351 { "response": { "incorrect": "attenenion", "correct": "attention" }, "expected": { "incorrect": "attenion", "correct": "attention" } }
[+]
0015_spell_check:attention:6 100 338 { "response": { "incorrect": "attenion", "correct": "attention" }, "expected": { "incorrect": "attenion", "correct": "attention" } }
[+]
0015_spell_check:attention:7 100 329 { "response": { "incorrect": "attetion", "correct": "attention" }, "expected": { "incorrect": "attetion", "correct": "attention" } }
[+]
0015_spell_check:attention:8 0 372 { "response": { "incorrect": "attention", "correct": "attention" }, "expected": { "incorrect": "atttention", "correct": "attention" } }
[+]
0015_spell_check:attention:9 100 377 { "response": { "incorrect": "attenttion", "correct": "attention" }, "expected": { "incorrect": "attenttion", "correct": "attention" } }
[+]
0015_spell_check:demonstrate:0 100 551 { "response": { "incorrect": "demonstraite", "correct": "demonstrate" }, "expected": { "incorrect": "demonstraite", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:1 100 799 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:2 100 456 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:3 100 399 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:4 100 378 { "response": { "incorrect": "demanstrate", "correct": "demonstrate" }, "expected": { "incorrect": "demanstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:5 100 375 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:6 100 377 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:7 100 388 { "response": { "incorrect": "demonstarte", "correct": "demonstrate" }, "expected": { "incorrect": "demonstarte", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:8 100 389 { "response": { "incorrect": "deomstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:demonstrate:9 100 463 { "response": { "incorrect": "deomonstrate", "correct": "demonstrate" }, "expected": { "incorrect": "deomonstrate", "correct": "demonstrate" } }
[+]
0015_spell_check:laboratory:0 100 633 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:1 100 498 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:2 100 388 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:3 100 379 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:4 100 377 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:5 100 372 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:6 100 375 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:7 100 398 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:8 100 451 { "response": { "incorrect": "labratory", "correct": "laboratory" }, "expected": { "incorrect": "labratory", "correct": "laboratory" } }
[+]
0015_spell_check:laboratory:9 100 461 { "response": { "incorrect": "laberatory", "correct": "laboratory" }, "expected": { "incorrect": "laberatory", "correct": "laboratory" } }
[+]
0015_spell_check:laughter:0 100 414 { "response": { "incorrect": "laughterr", "correct": "laughter" }, "expected": { "incorrect": "laughterr", "correct": "laughter" } }
[+]
0015_spell_check:laughter:1 0 454 { "response": { "incorrect": "laghter", "correct": "leader" }, "expected": { "incorrect": "laghter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:2 0 380 { "response": { "incorrect": "laghter", "correct": "leader" }, "expected": { "incorrect": "laghter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:3 0 388 { "response": { "incorrect": "lagter", "correct": "letter" }, "expected": { "incorrect": "laghter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:4 0 374 { "response": { "incorrect": "lafter", "correct": "feel" }, "expected": { "incorrect": "lafter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:5 0 380 { "response": { "incorrect": "laghter", "correct": "leader" }, "expected": { "incorrect": "laghter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:6 0 380 { "response": { "incorrect": " laugther", "correct": "laugher" }, "expected": { "incorrect": "laugther", "correct": "laughter" } }
[+]
0015_spell_check:laughter:7 100 388 { "response": { "incorrect": "laughtter", "correct": "laughter" }, "expected": { "incorrect": "laughtter", "correct": "laughter" } }
[+]
0015_spell_check:laughter:8 100 393 { "response": { "incorrect": "laughtur", "correct": "laughter" }, "expected": { "incorrect": "laughtur", "correct": "laughter" } }
[+]
0015_spell_check:laughter:9 0 448 { "response": { "incorrect": " laugther", "correct": "laugh" }, "expected": { "incorrect": "laugther", "correct": "laughter" } }
[+]
0015_spell_check:liaison:0 0 522 { "response": { "incorrect": "liason", "correct": "leader" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:1 0 462 { "response": { "incorrect": "liasion", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:2 100 416 { "response": { "incorrect": "liasion", "correct": "liaison" }, "expected": { "incorrect": "liasion", "correct": "liaison" } }
[+]
0015_spell_check:liaison:3 100 401 { "response": { "incorrect": "liason", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:4 100 398 { "response": { "incorrect": "liason", "correct": "liaison" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:5 0 399 { "response": { "incorrect": "liason", "correct": "leader" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:6 100 388 { "response": { "incorrect": "liasion", "correct": "liaison" }, "expected": { "incorrect": "liasion", "correct": "liaison" } }
[+]
0015_spell_check:liaison:7 0 390 { "response": { "incorrect": "leason", "correct": "lesson" }, "expected": { "incorrect": "leason", "correct": "liaison" } }
[+]
0015_spell_check:liaison:8 100 468 { "response": { "incorrect": "liasion", "correct": "liaison" }, "expected": { "incorrect": "liasion", "correct": "liaison" } }
[+]
0015_spell_check:liaison:9 0 475 { "response": { "incorrect": "liason", "correct": "lance" }, "expected": { "incorrect": "liason", "correct": "liaison" } }
[+]
0015_spell_check:orange:0 100 451 { "response": { "incorrect": "orrange", "correct": "orange" }, "expected": { "incorrect": "orrange", "correct": "orange" } }
[+]
0015_spell_check:orange:1 100 412 { "response": { "incorrect": "oranje", "correct": "orange" }, "expected": { "incorrect": "oranje", "correct": "orange" } }
[+]
0015_spell_check:orange:2 0 393 { "response": { "incorrect": "peeled", "correct": "peeled" }, "expected": { "incorrect": "orang", "correct": "orange" } }
[+]
0015_spell_check:orange:3 0 381 { "response": { "incorrect": " oranage", "correct": "orange" }, "expected": { "incorrect": "oranage", "correct": "orange" } }
[+]
0015_spell_check:orange:4 0 407 { "response": { "incorrect": "peeled", "correct": "peeled" }, "expected": { "incorrect": "oranage", "correct": "orange" } }
[+]
0015_spell_check:orange:5 100 378 { "response": { "incorrect": "orrange", "correct": "orange" }, "expected": { "incorrect": "orrange", "correct": "orange" } }
[+]
0015_spell_check:orange:6 100 387 { "response": { "incorrect": "orrange", "correct": "orange" }, "expected": { "incorrect": "orrange", "correct": "orange" } }
[+]
0015_spell_check:orange:7 100 385 { "response": { "incorrect": "oringe", "correct": "orange" }, "expected": { "incorrect": "oringe", "correct": "orange" } }
[+]
0015_spell_check:orange:8 0 401 { "response": { "incorrect": "orengen", "correct": "orange" }, "expected": { "incorrect": "orennge", "correct": "orange" } }
[+]
0015_spell_check:orange:9 100 456 { "response": { "incorrect": "orrange", "correct": "orange" }, "expected": { "incorrect": "orrange", "correct": "orange" } }
[+]
0015_spell_check:partition:0 100 461 { "response": { "incorrect": "partioned", "correct": "partitioned" }, "expected": { "incorrect": "partioned", "correct": "partitioned" } }
[+]
0015_spell_check:partition:1 0 462 { "response": { "incorrect": "painter's", "correct": "painter's" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:2 100 434 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:3 100 409 { "response": { "incorrect": "partionned", "correct": "partitioned" }, "expected": { "incorrect": "partionned", "correct": "partitioned" } }
[+]
0015_spell_check:partition:4 100 366 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:5 100 363 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:6 0 357 { "response": { "incorrect": "partition", "correct": "part" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:7 0 344 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "particion", "correct": "partition" } }
[+]
0015_spell_check:partition:8 0 386 { "response": { "incorrect": "paint", "correct": "paint" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:partition:9 100 440 { "response": { "incorrect": "partion", "correct": "partition" }, "expected": { "incorrect": "partion", "correct": "partition" } }
[+]
0015_spell_check:party:0 100 505 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:1 0 453 { "response": { "incorrect": "partee", "correct": "part" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:2 0 414 { "response": { "incorrect": "parry", "correct": "party" }, "expected": { "incorrect": "pary", "correct": "party" } }
[+]
0015_spell_check:party:3 100 375 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:4 100 365 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:5 100 363 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:6 0 364 { "response": { "incorrect": "partee", "correct": "part" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:7 100 357 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:8 100 437 { "response": { "incorrect": "partee", "correct": "party" }, "expected": { "incorrect": "partee", "correct": "party" } }
[+]
0015_spell_check:party:9 100 499 { "response": { "incorrect": "pary", "correct": "party" }, "expected": { "incorrect": "pary", "correct": "party" } }
[+]
0015_spell_check:stable:0 100 453 { "response": { "incorrect": "staable", "correct": "stable" }, "expected": { "incorrect": "staable", "correct": "stable" } }
[+]
0015_spell_check:stable:1 100 400 { "response": { "incorrect": "stabe", "correct": "stable" }, "expected": { "incorrect": "stabe", "correct": "stable" } }
[+]
0015_spell_check:stable:2 100 398 { "response": { "incorrect": "stabal", "correct": "stable" }, "expected": { "incorrect": "stabal", "correct": "stable" } }
[+]
0015_spell_check:stable:3 0 376 { "response": { "incorrect": "months", "correct": "months" }, "expected": { "incorrect": "staible", "correct": "stable" } }
[+]
0015_spell_check:stable:4 100 367 { "response": { "incorrect": "stabel", "correct": "stable" }, "expected": { "incorrect": "stabel", "correct": "stable" } }
[+]
0015_spell_check:stable:5 0 371 { "response": { "incorrect": "wobbly", "correct": "stable" }, "expected": { "incorrect": "staible", "correct": "stable" } }
[+]
0015_spell_check:stable:6 100 363 { "response": { "incorrect": "stabl", "correct": "stable" }, "expected": { "incorrect": "stabl", "correct": "stable" } }
[+]
0015_spell_check:stable:7 100 372 { "response": { "incorrect": "stabe", "correct": "stable" }, "expected": { "incorrect": "stabe", "correct": "stable" } }
[+]
0015_spell_check:stable:8 100 384 { "response": { "incorrect": "stabble", "correct": "stable" }, "expected": { "incorrect": "stabble", "correct": "stable" } }
[+]
0015_spell_check:stable:9 100 441 { "response": { "incorrect": "stayble", "correct": "stable" }, "expected": { "incorrect": "stayble", "correct": "stable" } }
[+]
0015_spell_check:table:0 100 445 { "response": { "incorrect": "tabele", "correct": "table" }, "expected": { "incorrect": "tabele", "correct": "table" } }
[+]
0015_spell_check:table:1 100 450 { "response": { "incorrect": "tabble", "correct": "table" }, "expected": { "incorrect": "tabble", "correct": "table" } }
[+]
0015_spell_check:table:2 100 449 { "response": { "incorrect": "tabel", "correct": "table" }, "expected": { "incorrect": "tabel", "correct": "table" } }
[+]
0015_spell_check:table:3 100 459 { "response": { "incorrect": "tabble", "correct": "table" }, "expected": { "incorrect": "tabble", "correct": "table" } }
[+]
0015_spell_check:table:4 100 439 { "response": { "incorrect": "tabble", "correct": "table" }, "expected": { "incorrect": "tabble", "correct": "table" } }
[+]
0015_spell_check:table:5 0 385 { "response": { "incorrect": "books", "correct": "books" }, "expected": { "incorrect": "tabl", "correct": "table" } }
[+]
0015_spell_check:table:6 0 353 { "response": { "incorrect": "gathered", "correct": "gathered" }, "expected": { "incorrect": "tabl", "correct": "table" } }
[+]
0015_spell_check:table:7 100 359 { "response": { "incorrect": "tabel", "correct": "table" }, "expected": { "incorrect": "tabel", "correct": "table" } }
[+]
0015_spell_check:table:8 0 341 { "response": { "incorrect": "dirty", "correct": "dirty" }, "expected": { "incorrect": "tabel", "correct": "table" } }
[+]
0015_spell_check:table:9 0 353 { "response": { "incorrect": "table", "correct": "table" }, "expected": { "incorrect": "tabel", "correct": "table" } }
[+]