Benchmark Run Details

Run Summary

Model phi4:14b:Q4_K_M
Benchmark 0050_translation_sw_ko
Normed Score 66
Run Timestamp 2025-03-26 20:08:30

Question-Level Details

Question ID Score Evaluation Time (ms) Debug Info
0050_translation_sw_ko:0 0 9704 { "response": "숨다", "expected": "꽃" }
[+]
0050_translation_sw_ko:1 100 3775 {}
[+]
0050_translation_sw_ko:10 0 3384 { "response": "다섯", "expected": "산" }
[+]
0050_translation_sw_ko:11 100 4370 {}
[+]
0050_translation_sw_ko:12 100 3827 {}
[+]
0050_translation_sw_ko:13 0 5641 { "response": "별", "expected": "밝은" }
[+]
0050_translation_sw_ko:14 100 5652 {}
[+]
0050_translation_sw_ko:15 0 4325 { "response": "화학", "expected": "조용한" }
[+]
0050_translation_sw_ko:16 100 3137 {}
[+]
0050_translation_sw_ko:17 100 3843 {}
[+]
0050_translation_sw_ko:18 0 3746 { "response": "바람", "expected": "하늘" }
[+]
0050_translation_sw_ko:19 0 3491 { "response": "물", "expected": "신선한" }
[+]
0050_translation_sw_ko:2 100 3135 {}
[+]
0050_translation_sw_ko:20 100 3512 {}
[+]
0050_translation_sw_ko:21 100 3626 {}
[+]
0050_translation_sw_ko:22 0 3411 { "response": "나무", "expected": "둥근" }
[+]
0050_translation_sw_ko:23 100 5570 {}
[+]
0050_translation_sw_ko:24 100 8399 {}
[+]
0050_translation_sw_ko:25 100 3850 {}
[+]
0050_translation_sw_ko:26 0 4413 { "response": "코끼리", "expected": "깊은" }
[+]
0050_translation_sw_ko:27 0 4547 { "response": "깊어지다", "expected": "수영하다" }
[+]
0050_translation_sw_ko:28 100 3333 {}
[+]
0050_translation_sw_ko:29 0 3537 { "response": "손님", "expected": "달콤한" }
[+]
0050_translation_sw_ko:3 100 3324 {}
[+]
0050_translation_sw_ko:30 100 3149 {}
[+]
0050_translation_sw_ko:31 0 2917 { "response": "구름", "expected": "미소짓다" }
[+]
0050_translation_sw_ko:32 0 2987 { "response": "친구", "expected": "부드러운" }
[+]
0050_translation_sw_ko:33 100 2494 {}
[+]
0050_translation_sw_ko:34 100 2818 {}
[+]
0050_translation_sw_ko:35 100 2985 {}
[+]
0050_translation_sw_ko:36 100 2706 {}
[+]
0050_translation_sw_ko:37 100 3179 {}
[+]
0050_translation_sw_ko:38 0 2814 { "response": "잔디", "expected": "무거운" }
[+]
0050_translation_sw_ko:39 0 2672 { "response": "닐", "expected": "불" }
[+]
0050_translation_sw_ko:4 0 2991 { "response": "구름", "expected": "먹다" }
[+]
0050_translation_sw_ko:40 100 3538 {}
[+]
0050_translation_sw_ko:41 100 3357 {}
[+]
0050_translation_sw_ko:42 100 2990 {}
[+]
0050_translation_sw_ko:43 100 3585 {}
[+]
0050_translation_sw_ko:44 0 3972 { "response": "달리다", "expected": "매끄러운" }
[+]
0050_translation_sw_ko:45 100 3288 {}
[+]
0050_translation_sw_ko:46 100 3749 {}
[+]
0050_translation_sw_ko:47 100 3171 {}
[+]
0050_translation_sw_ko:48 100 3082 {}
[+]
0050_translation_sw_ko:49 100 3814 {}
[+]
0050_translation_sw_ko:5 100 4122 {}
[+]
0050_translation_sw_ko:50 0 3114 { "response": "나무", "expected": "가벼운" }
[+]
0050_translation_sw_ko:6 100 4205 {}
[+]
0050_translation_sw_ko:7 100 3556 {}
[+]
0050_translation_sw_ko:8 100 3824 {}
[+]
0050_translation_sw_ko:9 100 5032 {}
[+]