Benchmark Run Details

Run Summary

Model qwen2.5:7b:Q4_K_M
Benchmark 0050_translation_sw_ko
Normed Score 23
Run Timestamp 2025-03-26 20:05:13

Question-Level Details

Question ID Score Evaluation Time (ms) Debug Info
0050_translation_sw_ko:0 0 4478 { "response": "숨다", "expected": "꽃" }
[+]
0050_translation_sw_ko:1 0 1112 { "response": "따뜻한", "expected": "운전하다" }
[+]
0050_translation_sw_ko:10 0 1765 { "response": "친구", "expected": "산" }
[+]
0050_translation_sw_ko:11 0 1967 { "response": "책", "expected": "노래하다" }
[+]
0050_translation_sw_ko:12 0 2323 { "response": "나무", "expected": "심장" }
[+]
0050_translation_sw_ko:13 0 1796 { "response": "별", "expected": "밝은" }
[+]
0050_translation_sw_ko:14 0 3357 { "response": "친구", "expected": "춤추다" }
[+]
0050_translation_sw_ko:15 0 2016 { "response": "화학", "expected": "조용한" }
[+]
0050_translation_sw_ko:16 0 1857 { "response": "심장", "expected": "나무" }
[+]
0050_translation_sw_ko:17 0 1921 { "response": "추운", "expected": "쓰다" }
[+]
0050_translation_sw_ko:18 0 1674 { "response": "바람", "expected": "하늘" }
[+]
0050_translation_sw_ko:19 0 1800 { "response": "跳舞", "expected": "신선한" }
[+]
0050_translation_sw_ko:2 0 3113 { "response": "심장", "expected": "가장 강한" }
[+]
0050_translation_sw_ko:20 100 2218 {}
[+]
0050_translation_sw_ko:21 100 2809 {}
[+]
0050_translation_sw_ko:22 0 2310 { "response": "매끄러운", "expected": "둥근" }
[+]
0050_translation_sw_ko:23 0 2091 { "response": "나무", "expected": "바람" }
[+]
0050_translation_sw_ko:24 0 2394 { "response": "달콤한", "expected": "따뜻한" }
[+]
0050_translation_sw_ko:25 0 1756 { "response": "불", "expected": "돌" }
[+]
0050_translation_sw_ko:26 0 1652 { "response": "새", "expected": "깊은" }
[+]
0050_translation_sw_ko:27 0 1599 { "response": "깊은", "expected": "수영하다" }
[+]
0050_translation_sw_ko:28 100 1620 {}
[+]
0050_translation_sw_ko:29 100 1600 {}
[+]
0050_translation_sw_ko:3 100 1467 {}
[+]
0050_translation_sw_ko:30 0 1521 { "response": "수영", "expected": "구름" }
[+]
0050_translation_sw_ko:31 0 1674 { "response": "밝은", "expected": "미소짓다" }
[+]
0050_translation_sw_ko:32 0 1673 { "response": "친구", "expected": "부드러운" }
[+]
0050_translation_sw_ko:33 0 2408 { "response": "부드러운", "expected": "비" }
[+]
0050_translation_sw_ko:34 0 2641 { "response": "날카로운", "expected": "자라다" }
[+]
0050_translation_sw_ko:35 100 1751 {}
[+]
0050_translation_sw_ko:36 100 1508 {}
[+]
0050_translation_sw_ko:37 100 1488 {}
[+]
0050_translation_sw_ko:38 0 1481 { "response": "잔디", "expected": "무거운" }
[+]
0050_translation_sw_ko:39 100 1724 {}
[+]
0050_translation_sw_ko:4 0 1729 { "response": "구름", "expected": "먹다" }
[+]
0050_translation_sw_ko:40 0 1887 { "response": "달콤한", "expected": "숨쉬다" }
[+]
0050_translation_sw_ko:41 0 1669 { "response": "꽃", "expected": "날카로운" }
[+]
0050_translation_sw_ko:42 0 1561 { "response": "책", "expected": "소금" }
[+]
0050_translation_sw_ko:43 0 1817 { "response": "날카로운", "expected": "숨다" }
[+]
0050_translation_sw_ko:44 100 1809 {}
[+]
0050_translation_sw_ko:45 0 1723 { "response": "달콤한", "expected": "잔디" }
[+]
0050_translation_sw_ko:46 0 1763 { "response": "조용한", "expected": "날다" }
[+]
0050_translation_sw_ko:47 0 1799 { "response": "신선한", "expected": "추운" }
[+]
0050_translation_sw_ko:48 0 1557 { "response": "책", "expected": "모래" }
[+]
0050_translation_sw_ko:49 0 1413 { "response": "웃다", "expected": "떨어지다" }
[+]
0050_translation_sw_ko:5 0 1940 { "response": "따뜻한", "expected": "아름다운" }
[+]
0050_translation_sw_ko:50 0 1339 { "response": "나무", "expected": "가벼운" }
[+]
0050_translation_sw_ko:6 100 2381 {}
[+]
0050_translation_sw_ko:7 0 2745 { "response": "미소짓다", "expected": "자다" }
[+]
0050_translation_sw_ko:8 100 2183 {}
[+]
0050_translation_sw_ko:9 0 1788 { "response": "구름", "expected": "웃다" }
[+]