Benchmark Run Details

Run Summary

Model gemma3:4b:Q4_K_M
Benchmark 0050_translation_sw_ko
Normed Score 39
Run Timestamp 2025-03-26 20:09:19

Question-Level Details

Question ID Score Evaluation Time (ms) Debug Info
0050_translation_sw_ko:0 0 1770 { "response": "비", "expected": "꽃" }
[+]
0050_translation_sw_ko:1 0 597 { "response": "불", "expected": "운전하다" }
[+]
0050_translation_sw_ko:10 0 681 { "response": "친구", "expected": "산" }
[+]
0050_translation_sw_ko:11 0 762 { "response": "구름", "expected": "노래하다" }
[+]
0050_translation_sw_ko:12 0 777 { "response": "춤추다", "expected": "심장" }
[+]
0050_translation_sw_ko:13 0 820 { "response": "별", "expected": "밝은" }
[+]
0050_translation_sw_ko:14 100 1663 {}
[+]
0050_translation_sw_ko:15 100 863 {}
[+]
0050_translation_sw_ko:16 100 704 {}
[+]
0050_translation_sw_ko:17 100 689 {}
[+]
0050_translation_sw_ko:18 0 705 { "response": "바람", "expected": "하늘" }
[+]
0050_translation_sw_ko:19 100 788 {}
[+]
0050_translation_sw_ko:2 0 866 { "response": "친구", "expected": "가장 강한" }
[+]
0050_translation_sw_ko:20 100 728 {}
[+]
0050_translation_sw_ko:21 0 760 { "response": "모래", "expected": "달리다" }
[+]
0050_translation_sw_ko:22 0 755 { "response": "바람", "expected": "둥근" }
[+]
0050_translation_sw_ko:23 100 723 {}
[+]
0050_translation_sw_ko:24 0 762 { "response": "깊은", "expected": "따뜻한" }
[+]
0050_translation_sw_ko:25 0 621 { "response": "바람", "expected": "돌" }
[+]
0050_translation_sw_ko:26 0 1082 { "response": "모래", "expected": "깊은" }
[+]
0050_translation_sw_ko:27 0 808 { "response": "구름", "expected": "수영하다" }
[+]
0050_translation_sw_ko:28 100 704 {}
[+]
0050_translation_sw_ko:29 0 756 { "response": "춤추다", "expected": "달콤한" }
[+]
0050_translation_sw_ko:3 100 1406 {}
[+]
0050_translation_sw_ko:30 0 663 { "response": "새", "expected": "구름" }
[+]
0050_translation_sw_ko:31 100 811 {}
[+]
0050_translation_sw_ko:32 100 919 {}
[+]
0050_translation_sw_ko:33 0 1100 { "response": "빠른", "expected": "비" }
[+]
0050_translation_sw_ko:34 100 1230 {}
[+]
0050_translation_sw_ko:35 0 1362 { "response": "춤추다", "expected": "빠른" }
[+]
0050_translation_sw_ko:36 100 809 {}
[+]
0050_translation_sw_ko:37 100 870 {}
[+]
0050_translation_sw_ko:38 0 862 { "response": "신선한", "expected": "무거운" }
[+]
0050_translation_sw_ko:39 0 887 { "response": "날카로운", "expected": "불" }
[+]
0050_translation_sw_ko:4 0 1039 { "response": "구름", "expected": "먹다" }
[+]
0050_translation_sw_ko:40 0 1128 { "response": "미소짓다", "expected": "숨쉬다" }
[+]
0050_translation_sw_ko:41 100 790 {}
[+]
0050_translation_sw_ko:42 0 839 { "response": "따뜻한", "expected": "소금" }
[+]
0050_translation_sw_ko:43 0 912 { "response": "춤추다", "expected": "숨다" }
[+]
0050_translation_sw_ko:44 0 716 { "response": "달", "expected": "매끄러운" }
[+]
0050_translation_sw_ko:45 100 1102 {}
[+]
0050_translation_sw_ko:46 0 976 { "response": "날카로운", "expected": "날다" }
[+]
0050_translation_sw_ko:47 0 1261 { "response": "나무", "expected": "추운" }
[+]
0050_translation_sw_ko:48 100 1022 {}
[+]
0050_translation_sw_ko:49 0 977 { "response": "달콤한", "expected": "떨어지다" }
[+]
0050_translation_sw_ko:5 0 773 { "response": "좋은", "expected": "아름다운" }
[+]
0050_translation_sw_ko:50 0 779 { "response": "새", "expected": "가벼운" }
[+]
0050_translation_sw_ko:6 100 694 {}
[+]
0050_translation_sw_ko:7 100 763 {}
[+]
0050_translation_sw_ko:8 100 762 {}
[+]
0050_translation_sw_ko:9 0 772 { "response": "깊은", "expected": "웃다" }
[+]