Benchmark Run Details

System Prompt

You are helping with a language translation task.
When translating a word from SW to KO:
- Provide the most direct and common translation
- Give only the base form of the word
- Do not include articles unless they are part of the standard translation
- Do not provide explanations or alternative translations

Run Summary

Model claude-3-5-haiku-20241022
Benchmark 0050_translation_sw_ko
Normed Score 78
Run Timestamp 2025-04-02 19:08:59

Question-Level Details

Question ID Score Evaluation Time (ms) Debug Info
0050_translation_sw_ko:0 0 756 { "response": "숨다", "expected": "꽃", "is_correct": false }
[+]
0050_translation_sw_ko:1 100 1129 { "response": "운전하다", "expected": "운전하다", "is_correct": true }
[+]
0050_translation_sw_ko:10 100 1130 { "response": "산", "expected": "산", "is_correct": true }
[+]
0050_translation_sw_ko:11 100 703 { "response": "노래하다", "expected": "노래하다", "is_correct": true }
[+]
0050_translation_sw_ko:12 100 734 { "response": "심장", "expected": "심장", "is_correct": true }
[+]
0050_translation_sw_ko:13 0 1324 { "response": "수영하다", "expected": "밝은", "is_correct": false }
[+]
0050_translation_sw_ko:14 100 1174 { "response": "춤추다", "expected": "춤추다", "is_correct": true }
[+]
0050_translation_sw_ko:15 100 813 { "response": "조용한", "expected": "조용한", "is_correct": true }
[+]
0050_translation_sw_ko:16 100 1151 { "response": "나무", "expected": "나무", "is_correct": true }
[+]
0050_translation_sw_ko:17 100 738 { "response": "쓰다", "expected": "쓰다", "is_correct": true }
[+]
0050_translation_sw_ko:18 0 825 { "response": "바람", "expected": "하늘", "is_correct": false }
[+]
0050_translation_sw_ko:19 100 672 { "response": "신선한", "expected": "신선한", "is_correct": true }
[+]
0050_translation_sw_ko:2 0 1240 { "response": "강한", "expected": "가장 강한", "is_correct": false }
[+]
0050_translation_sw_ko:20 100 763 { "response": "친구", "expected": "친구", "is_correct": true }
[+]
0050_translation_sw_ko:21 100 1144 { "response": "달리다", "expected": "달리다", "is_correct": true }
[+]
0050_translation_sw_ko:22 0 693 { "response": "바람", "expected": "둥근", "is_correct": false }
[+]
0050_translation_sw_ko:23 100 660 { "response": "바람", "expected": "바람", "is_correct": true }
[+]
0050_translation_sw_ko:24 0 1285 { "response": "심장", "expected": "따뜻한", "is_correct": false }
[+]
0050_translation_sw_ko:25 100 772 { "response": "돌", "expected": "돌", "is_correct": true }
[+]
0050_translation_sw_ko:26 0 1115 { "response": "새", "expected": "깊은", "is_correct": false }
[+]
0050_translation_sw_ko:27 100 1142 { "response": "수영하다", "expected": "수영하다", "is_correct": true }
[+]
0050_translation_sw_ko:28 100 762 { "response": "새", "expected": "새", "is_correct": true }
[+]
0050_translation_sw_ko:29 100 811 { "response": "달콤한", "expected": "달콤한", "is_correct": true }
[+]
0050_translation_sw_ko:3 100 802 { "response": "책", "expected": "책", "is_correct": true }
[+]
0050_translation_sw_ko:30 100 1161 { "response": "구름", "expected": "구름", "is_correct": true }
[+]
0050_translation_sw_ko:31 100 1449 { "response": "미소짓다", "expected": "미소짓다", "is_correct": true }
[+]
0050_translation_sw_ko:32 0 1158 { "response": "친구", "expected": "부드러운", "is_correct": false }
[+]
0050_translation_sw_ko:33 100 680 { "response": "비", "expected": "비", "is_correct": true }
[+]
0050_translation_sw_ko:34 100 760 { "response": "자라다", "expected": "자라다", "is_correct": true }
[+]
0050_translation_sw_ko:35 100 1200 { "response": "빠른", "expected": "빠른", "is_correct": true }
[+]
0050_translation_sw_ko:36 100 721 { "response": "별", "expected": "별", "is_correct": true }
[+]
0050_translation_sw_ko:37 100 1214 { "response": "춤추다", "expected": "춤추다", "is_correct": true }
[+]
0050_translation_sw_ko:38 0 1221 { "response": "나무", "expected": "무거운", "is_correct": false }
[+]
0050_translation_sw_ko:39 100 713 { "response": "불", "expected": "불", "is_correct": true }
[+]
0050_translation_sw_ko:4 100 723 { "response": "먹다", "expected": "먹다", "is_correct": true }
[+]
0050_translation_sw_ko:40 100 1186 { "response": "숨쉬다", "expected": "숨쉬다", "is_correct": true }
[+]
0050_translation_sw_ko:41 0 751 { "response": "꽃", "expected": "날카로운", "is_correct": false }
[+]
0050_translation_sw_ko:42 100 827 { "response": "소금", "expected": "소금", "is_correct": true }
[+]
0050_translation_sw_ko:43 100 711 { "response": "숨다", "expected": "숨다", "is_correct": true }
[+]
0050_translation_sw_ko:44 0 715 { "response": "소금", "expected": "매끄러운", "is_correct": false }
[+]
0050_translation_sw_ko:45 100 704 { "response": "잔디", "expected": "잔디", "is_correct": true }
[+]
0050_translation_sw_ko:46 100 774 { "response": "날다", "expected": "날다", "is_correct": true }
[+]
0050_translation_sw_ko:47 100 684 { "response": "추운", "expected": "추운", "is_correct": true }
[+]
0050_translation_sw_ko:48 100 1214 { "response": "모래", "expected": "모래", "is_correct": true }
[+]
0050_translation_sw_ko:49 100 714 { "response": "떨어지다", "expected": "떨어지다", "is_correct": true }
[+]
0050_translation_sw_ko:5 100 736 { "response": "아름다운", "expected": "아름다운", "is_correct": true }
[+]
0050_translation_sw_ko:50 100 1236 { "response": "가벼운", "expected": "가벼운", "is_correct": true }
[+]
0050_translation_sw_ko:6 100 821 { "response": "물", "expected": "물", "is_correct": true }
[+]
0050_translation_sw_ko:7 100 1178 { "response": "자다", "expected": "자다", "is_correct": true }
[+]
0050_translation_sw_ko:8 100 688 { "response": "달", "expected": "달", "is_correct": true }
[+]
0050_translation_sw_ko:9 100 763 { "response": "웃다", "expected": "웃다", "is_correct": true }
[+]