Update benchmark leaderboard
Browse files- index.html +276 -193
index.html
CHANGED
|
@@ -6,250 +6,333 @@
|
|
| 6 |
<title>Text Quality Rating Benchmark</title>
|
| 7 |
<link rel="preconnect" href="https://fonts.googleapis.com"/>
|
| 8 |
<link href="https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@400;600;700&family=Syne:wght@700;800&display=swap" rel="stylesheet"/>
|
|
|
|
| 9 |
<style>
|
| 10 |
*, *::before, *::after { box-sizing: border-box; margin: 0; padding: 0; }
|
| 11 |
body {
|
| 12 |
-
background: #0d1117;
|
| 13 |
-
color: #e2e8f0;
|
| 14 |
font-family: 'JetBrains Mono', monospace;
|
| 15 |
-
padding: 36px 28px
|
| 16 |
-
min-height: 100vh;
|
| 17 |
}
|
| 18 |
h1 {
|
| 19 |
font-family: 'Syne', sans-serif;
|
| 20 |
-
font-size: clamp(
|
| 21 |
-
|
| 22 |
-
letter-spacing: -0.02em;
|
| 23 |
-
color: #f1f5f9;
|
| 24 |
-
margin-bottom: 8px;
|
| 25 |
}
|
| 26 |
-
.subtitle {
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
.filter-label {
|
| 33 |
-
font-size: 10px;
|
| 34 |
-
text-transform: uppercase;
|
| 35 |
-
letter-spacing: 0.1em;
|
| 36 |
-
color: #475569;
|
| 37 |
-
margin-bottom: 10px;
|
| 38 |
-
}
|
| 39 |
-
#chips {
|
| 40 |
-
display: flex;
|
| 41 |
-
flex-wrap: wrap;
|
| 42 |
-
gap: 6px;
|
| 43 |
-
margin-bottom: 28px;
|
| 44 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
.chip {
|
| 46 |
-
padding: 4px 11px;
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
cursor: pointer;
|
| 51 |
-
border: 1px solid #2d3748;
|
| 52 |
-
background: #161b26;
|
| 53 |
-
color: #94a3b8;
|
| 54 |
-
transition: border-color .15s, color .15s, background .15s;
|
| 55 |
-
user-select: none;
|
| 56 |
}
|
| 57 |
.chip:hover { border-color: #7dd3fc; color: #e2e8f0; }
|
| 58 |
.chip.active { background: #1e3a5f; border-color: #38bdf8; color: #7dd3fc; }
|
| 59 |
-
|
| 60 |
-
.
|
| 61 |
-
|
| 62 |
-
border-radius:
|
| 63 |
-
|
| 64 |
-
}
|
| 65 |
-
table {
|
| 66 |
-
border-collapse: collapse;
|
| 67 |
-
width: 100%;
|
| 68 |
-
font-size: 12.5px;
|
| 69 |
}
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
border
|
| 73 |
}
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
|
|
|
|
|
|
| 77 |
}
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
th
|
| 81 |
-
th.
|
|
|
|
|
|
|
| 82 |
.sort-btn {
|
| 83 |
-
background: none;
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
font: inherit;
|
| 88 |
-
font-size: 10px;
|
| 89 |
-
font-weight: 700;
|
| 90 |
-
text-transform: uppercase;
|
| 91 |
-
letter-spacing: 0.08em;
|
| 92 |
-
display: inline-flex;
|
| 93 |
-
align-items: center;
|
| 94 |
-
gap: 3px;
|
| 95 |
-
padding: 0;
|
| 96 |
-
white-space: nowrap;
|
| 97 |
}
|
| 98 |
.sort-btn:hover { color: #7dd3fc; }
|
| 99 |
.sort-btn.active { color: #e2e8f0; }
|
| 100 |
-
tbody tr {
|
| 101 |
-
border-bottom: 1px solid #0f1520;
|
| 102 |
-
transition: filter .1s;
|
| 103 |
-
}
|
| 104 |
tbody tr:hover { filter: brightness(1.15); }
|
| 105 |
-
td { padding:
|
| 106 |
td.rank { padding-left: 14px; color: #475569; font-weight: 700; font-size: 13px; }
|
| 107 |
td.model { padding-left: 14px; color: #cbd5e1; font-weight: 600; max-width: 280px; overflow: hidden; text-overflow: ellipsis; }
|
| 108 |
td.score {
|
| 109 |
-
text-align: center;
|
| 110 |
-
font-weight: 700;
|
| 111 |
-
font-size: 12px;
|
| 112 |
border-right: 1px solid rgba(255,255,255,0.04);
|
| 113 |
}
|
| 114 |
-
td.empty
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
font-size:
|
| 118 |
-
color: #
|
| 119 |
-
|
|
|
|
|
|
|
|
|
|
| 120 |
}
|
|
|
|
|
|
|
|
|
|
| 121 |
</style>
|
| 122 |
</head>
|
| 123 |
<body>
|
| 124 |
<h1>Text Quality Rating Benchmark</h1>
|
| 125 |
-
<p class="subtitle">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
|
| 127 |
<div class="filter-label">Filter by language</div>
|
| 128 |
<div id="chips"></div>
|
| 129 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 130 |
<div class="table-wrap">
|
| 131 |
<table id="lb-table">
|
| 132 |
<thead id="lb-head"></thead>
|
| 133 |
<tbody id="lb-body"></tbody>
|
| 134 |
</table>
|
| 135 |
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 136 |
<div class="footer" id="footer"></div>
|
| 137 |
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
const ALL_ROWS = [{"model": "Qwen/Qwen3.5-397B-A17B-FP8", "avg": 0.6479480432226639, "total": 17861, "lang_scores": {"ar": 0.675, "az": 0.7025, "be": 0.785, "bg": 0.7596685082872928, "bo": 0.735, "ca": 0.7325905292479109, "cn": 0.6283333333333333, "cs": 0.7425, "da": 0.565, "de": 0.67, "el": 0.6075, "en": 0.46, "es": 0.7777777777777778, "et": 0.6575, "eu": 0.474036850921273, "fa": 0.565, "fi": 0.77, "fr": 0.7696335078534031, "gl": 0.5216666666666666, "hu": 0.6475, "hv": 0.7175, "is": 0.715, "it": 0.78, "ka": 0.6886792452830188, "la": 0.6627680311890838, "li": 0.6, "lv": 0.725, "mk": 0.54, "mt": 0.74, "nl": 0.58, "no": 0.695, "pl": 0.4868651488616462, "pt": 0.695, "ro": 0.625, "ru": 0.759075907590759, "sk": 0.63, "sl": 0.715, "sq": 0.8025, "sr": 0.5625, "stack": 0.3843351548269581, "sv": 0.66, "tr": 0.55, "uk": 0.7647058823529411}}, {"model": "openai/gpt-4o-mini", "avg": 0.5879781420765028, "total": 1830, "lang_scores": {"ar": 0.6153846153846154, "az": 0.5, "be": 0.725, "bg": 0.675, "bo": 0.675, "ca": 0.475, "cn": 0.7, "cs": 0.6, "da": 0.525, "de": 0.55, "el": 0.525, "en": 0.425, "es": 0.8, "et": 0.875, "eu": 0.35, "fa": 0.5333333333333333, "fi": 0.65, "fr": 0.575, "gl": 0.43333333333333335, "hu": 0.65, "hv": 0.7, "is": 0.6, "it": 0.725, "ka": 0.475, "la": 0.4, "li": 0.675, "lv": 0.725, "mk": 0.4, "mt": 0.6, "nl": 0.475, "no": 0.675, "pl": 0.38333333333333336, "pt": 0.75, "ro": 0.5, "ru": 0.8484848484848485, "sk": 0.7, "sl": 0.7, "sq": 0.7, "sr": 0.475, "stack": 0.36666666666666664, "sv": 0.725, "tr": 0.65, "uk": 0.6842105263157895}}, {"model": "google/gemini-3-flash-preview", "avg": 0.5766503000545554, "total": 1833, "lang_scores": {"ar": 0.575, "az": 0.55, "be": 0.625, "bg": 0.75, "bo": 0.575, "ca": 0.725, "cn": 0.5666666666666667, "cs": 0.525, "da": 0.475, "de": 0.65, "el": 0.575, "en": 0.4, "es": 0.825, "et": 0.625, "eu": 0.4166666666666667, "fa": 0.5166666666666667, "fi": 0.625, "fr": 0.675, "gl": 0.5333333333333333, "hu": 0.575, "hv": 0.7, "is": 0.55, "it": 0.725, "ka": 0.6, "la": 0.5, "li": 0.5, "lv": 0.6, "mk": 0.525, "mt": 0.7, "nl": 0.45, "no": 0.6, "pl": 0.36666666666666664, "pt": 0.525, "ro": 0.625, "ru": 0.696969696969697, "sk": 0.525, "sl": 0.7, "sq": 0.675, "sr": 0.475, "stack": 0.5333333333333333, "sv": 0.6, "tr": 0.6, "uk": 0.6}}, {"model": "qwen/qwen3-235b-a22b-2507", "avg": 0.49318057828696127, "total": 1833, "lang_scores": {"ar": 0.6, "az": 0.475, "be": 0.55, "bg": 0.65, "bo": 0.55, "ca": 0.525, "cn": 0.43333333333333335, "cs": 0.425, "da": 0.45, "de": 0.65, "el": 0.55, "en": 0.425, "es": 0.525, "et": 0.5, "eu": 0.4166666666666667, "fa": 0.6166666666666667, "fi": 0.55, "fr": 0.6, "gl": 0.43333333333333335, "hu": 0.65, "hv": 0.625, "is": 0.475, "it": 0.65, "ka": 0.325, "la": 0.43333333333333335, "li": 0.4, "lv": 0.575, "mk": 0.35, "mt": 0.475, "nl": 0.35, "no": 0.4, "pl": 0.31666666666666665, "pt": 0.575, "ro": 0.5, "ru": 0.45454545454545453, "sk": 0.45, "sl": 0.575, "sq": 0.6, "sr": 0.5, "stack": 0.35, "sv": 0.475, "tr": 0.45, "uk": 0.625}}, {"model": "z-ai/glm-4-32b", "avg": 0.4249863611565739, "total": 1833, "lang_scores": {"ar": 0.375, "az": 0.5, "be": 0.625, "bg": 0.375, "bo": 0.625, "ca": 0.35, "cn": 0.38333333333333336, "cs": 0.625, "da": 0.35, "de": 0.4, "el": 0.55, "en": 0.3, "es": 0.35, "et": 0.525, "eu": 0.3, "fa": 0.38333333333333336, "fi": 0.525, "fr": 0.525, "gl": 0.25, "hu": 0.5, "hv": 0.625, "is": 0.35, "it": 0.4, "ka": 0.5, "la": 0.43333333333333335, "li": 0.425, "lv": 0.525, "mk": 0.225, "mt": 0.35, "nl": 0.425, "no": 0.475, "pl": 0.35, "pt": 0.25, "ro": 0.3, "ru": 0.5151515151515151, "sk": 0.525, "sl": 0.475, "sq": 0.7, "sr": 0.375, "stack": 0.21666666666666667, "sv": 0.4, "tr": 0.425, "uk": 0.525}}, {"model": "speakleash/Bielik-11B-v3.0-Instruct", "avg": 0.417804478427089, "total": 1831, "lang_scores": {"ar": 0.025, "az": 0.525, "be": 0.2, "bg": 0.525, "bo": 0.675, "ca": 0.325, "cn": 0.2711864406779661, "cs": 0.5, "da": 0.425, "de": 0.95, "el": 0.325, "en": 0.5, "es": 0.475, "et": 0.55, "eu": 0.25, "fa": 0.36666666666666664, "fi": 0.425, "fr": 0.5, "gl": 0.4, "hu": 0.475, "hv": 0.525, "is": 0.225, "it": 0.475, "ka": 0.23076923076923078, "la": 0.3, "li": 0.45, "lv": 0.425, "mk": 0.275, "mt": 0.375, "nl": 0.45, "no": 0.475, "pl": 0.36666666666666664, "pt": 0.475, "ro": 0.425, "ru": 0.6060606060606061, "sk": 0.475, "sl": 0.55, "sq": 0.5, "sr": 0.45, "stack": 0.3333333333333333, "sv": 0.425, "tr": 0.45, "uk": 0.625}}, {"model": "deepseek/deepseek-v3.2", "avg": 0.4064375340971086, "total": 1833, "lang_scores": {"ar": 0.375, "az": 0.325, "be": 0.475, "bg": 0.475, "bo": 0.475, "ca": 0.425, "cn": 0.5333333333333333, "cs": 0.5, "da": 0.275, "de": 0.6, "el": 0.25, "en": 0.525, "es": 0.425, "et": 0.425, "eu": 0.3333333333333333, "fa": 0.35, "fi": 0.375, "fr": 0.45, "gl": 0.48333333333333334, "hu": 0.4, "hv": 0.475, "is": 0.575, "it": 0.425, "ka": 0.35, "la": 0.3, "li": 0.375, "lv": 0.4, "mk": 0.325, "mt": 0.375, "nl": 0.325, "no": 0.4, "pl": 0.36666666666666664, "pt": 0.475, "ro": 0.25, "ru": 0.48484848484848486, "sk": 0.375, "sl": 0.6, "sq": 0.375, "sr": 0.3, "stack": 0.4166666666666667, "sv": 0.375, "tr": 0.375, "uk": 0.425}}, {"model": "google/gemini-2.0-flash-lite-001", "avg": 0.3791598472449536, "total": 1833, "lang_scores": {"ar": 0.325, "az": 0.325, "be": 0.55, "bg": 0.6, "bo": 0.4, "ca": 0.275, "cn": 0.45, "cs": 0.3, "da": 0.4, "de": 0.35, "el": 0.225, "en": 0.525, "es": 0.4, "et": 0.55, "eu": 0.3333333333333333, "fa": 0.5166666666666667, "fi": 0.4, "fr": 0.425, "gl": 0.38333333333333336, "hu": 0.45, "hv": 0.425, "is": 0.2, "it": 0.425, "ka": 0.3, "la": 0.21666666666666667, "li": 0.425, "lv": 0.475, "mk": 0.2, "mt": 0.425, "nl": 0.4, "no": 0.325, "pl": 0.36666666666666664, "pt": 0.375, "ro": 0.275, "ru": 0.6060606060606061, "sk": 0.425, "sl": 0.375, "sq": 0.425, "sr": 0.25, "stack": 0.21666666666666667, "sv": 0.425, "tr": 0.4, "uk": 0.275}}, {"model": "meta-llama/llama-4-scout", "avg": 0.3768432550518842, "total": 1831, "lang_scores": {"ar": 0.325, "az": 0.475, "be": 0.3, "bg": 0.375, "bo": 0.425, "ca": 0.3, "cn": 0.25, "cs": 0.525, "da": 0.375, "de": 0.6, "el": 0.275, "en": 0.225, "es": 0.475, "et": 0.425, "eu": 0.2542372881355932, "fa": 0.4, "fi": 0.5, "fr": 0.375, "gl": 0.2, "hu": 0.45, "hv": 0.45, "is": 0.55, "it": 0.425, "ka": 0.3, "la": 0.31666666666666665, "li": 0.35, "lv": 0.45, "mk": 0.275, "mt": 0.35, "nl": 0.325, "no": 0.475, "pl": 0.35, "pt": 0.5, "ro": 0.325, "ru": 0.5454545454545454, "sk": 0.5, "sl": 0.4, "sq": 0.575, "sr": 0.275, "stack": 0.21666666666666667, "sv": 0.425, "tr": 0.425, "uk": 0.3333333333333333}}, {"model": "meta-llama/llama-3.3-70b-instruct", "avg": 0.3669623059866962, "total": 1804, "lang_scores": {"ar": 0.38461538461538464, "az": 0.39473684210526316, "be": 0.475, "bg": 0.4, "bo": 0.45, "ca": 0.25, "cn": 0.3050847457627119, "cs": 0.525, "da": 0.358974358974359, "de": 0.45, "el": 0.4473684210526316, "en": 0.2564102564102564, "es": 0.32432432432432434, "et": 0.5128205128205128, "eu": 0.29310344827586204, "fa": 0.3103448275862069, "fi": 0.5384615384615384, "fr": 0.38461538461538464, "gl": 0.18333333333333332, "hu": 0.45, "hv": 0.4, "is": 0.45, "it": 0.38461538461538464, "ka": 0.35, "la": 0.3103448275862069, "li": 0.2564102564102564, "lv": 0.425, "mk": 0.225, "mt": 0.275, "nl": 0.425, "no": 0.375, "pl": 0.4, "pt": 0.358974358974359, "ro": 0.13157894736842105, "ru": 0.5151515151515151, "sk": 0.425, "sl": 0.4358974358974359, "sq": 0.28205128205128205, "sr": 0.3333333333333333, "stack": 0.35, "sv": 0.41025641025641024, "tr": 0.475, "uk": 0.35}}, {"model": "z-ai/glm-4.5-air", "avg": 0.36224768139661756, "total": 1833, "lang_scores": {"ar": 0.325, "az": 0.4, "be": 0.525, "bg": 0.475, "bo": 0.45, "ca": 0.375, "cn": 0.4, "cs": 0.35, "da": 0.325, "de": 0.4, "el": 0.325, "en": 0.275, "es": 0.35, "et": 0.6, "eu": 0.3, "fa": 0.2833333333333333, "fi": 0.45, "fr": 0.3, "gl": 0.38333333333333336, "hu": 0.375, "hv": 0.175, "is": 0.25, "it": 0.125, "ka": 0.35, "la": 0.15, "li": 0.175, "lv": 0.1, "mk": 0.2, "mt": 0.275, "nl": 0.225, "no": 0.375, "pl": 0.35, "pt": 0.525, "ro": 0.4, "ru": 0.48484848484848486, "sk": 0.55, "sl": 0.625, "sq": 0.65, "sr": 0.325, "stack": 0.35, "sv": 0.5, "tr": 0.45, "uk": 0.5}}, {"model": "google/gemma-3-12b-it", "avg": 0.337152209492635, "total": 1833, "lang_scores": {"ar": 0.275, "az": 0.35, "be": 0.35, "bg": 0.475, "bo": 0.45, "ca": 0.225, "cn": 0.38333333333333336, "cs": 0.45, "da": 0.375, "de": 0.5, "el": 0.275, "en": 0.45, "es": 0.325, "et": 0.4, "eu": 0.23333333333333334, "fa": 0.25, "fi": 0.4, "fr": 0.425, "gl": 0.16666666666666666, "hu": 0.35, "hv": 0.4, "is": 0.475, "it": 0.325, "ka": 0.3, "la": 0.3, "li": 0.25, "lv": 0.425, "mk": 0.275, "mt": 0.25, "nl": 0.45, "no": 0.375, "pl": 0.36666666666666664, "pt": 0.25, "ro": 0.25, "ru": 0.5757575757575758, "sk": 0.275, "sl": 0.35, "sq": 0.35, "sr": 0.325, "stack": 0.26666666666666666, "sv": 0.175, "tr": 0.325, "uk": 0.375}}, {"model": "mistralai/mistral-nemo", "avg": 0.3109656301145663, "total": 1833, "lang_scores": {"ar": 0.325, "az": 0.45, "be": 0.475, "bg": 0.325, "bo": 0.375, "ca": 0.25, "cn": 0.38333333333333336, "cs": 0.425, "da": 0.375, "de": 0.4, "el": 0.3, "en": 0.25, "es": 0.35, "et": 0.225, "eu": 0.21666666666666667, "fa": 0.26666666666666666, "fi": 0.35, "fr": 0.275, "gl": 0.2833333333333333, "hu": 0.2, "hv": 0.425, "is": 0.3, "it": 0.2, "ka": 0.425, "la": 0.18333333333333332, "li": 0.325, "lv": 0.425, "mk": 0.375, "mt": 0.325, "nl": 0.35, "no": 0.375, "pl": 0.25, "pt": 0.35, "ro": 0.2, "ru": 0.21212121212121213, "sk": 0.375, "sl": 0.35, "sq": 0.3, "sr": 0.25, "stack": 0.3333333333333333, "sv": 0.175, "tr": 0.275, "uk": 0.25}}, {"model": "openai/gpt-4.1-nano", "avg": 0.2898471615720524, "total": 1832, "lang_scores": {"ar": 0.2564102564102564, "az": 0.275, "be": 0.25, "bg": 0.35, "bo": 0.325, "ca": 0.125, "cn": 0.4, "cs": 0.35, "da": 0.375, "de": 0.0, "el": 0.225, "en": 0.1, "es": 0.275, "et": 0.45, "eu": 0.2, "fa": 0.36666666666666664, "fi": 0.5, "fr": 0.325, "gl": 0.3, "hu": 0.25, "hv": 0.35, "is": 0.3, "it": 0.3, "ka": 0.125, "la": 0.2, "li": 0.275, "lv": 0.425, "mk": 0.125, "mt": 0.25, "nl": 0.3, "no": 0.275, "pl": 0.3, "pt": 0.225, "ro": 0.25, "ru": 0.3939393939393939, "sk": 0.275, "sl": 0.3, "sq": 0.325, "sr": 0.325, "stack": 0.2833333333333333, "sv": 0.375, "tr": 0.325, "uk": 0.325}}, {"model": "qwen/qwen-2.5-7b-instruct", "avg": 0.2618657937806874, "total": 1833, "lang_scores": {"ar": 0.2, "az": 0.15, "be": 0.25, "bg": 0.35, "bo": 0.4, "ca": 0.225, "cn": 0.31666666666666665, "cs": 0.3, "da": 0.325, "de": 0.25, "el": 0.2, "en": 0.4, "es": 0.325, "et": 0.25, "eu": 0.21666666666666667, "fa": 0.3, "fi": 0.275, "fr": 0.35, "gl": 0.36666666666666664, "hu": 0.225, "hv": 0.3, "is": 0.325, "it": 0.3, "ka": 0.125, "la": 0.18333333333333332, "li": 0.2, "lv": 0.35, "mk": 0.15, "mt": 0.225, "nl": 0.275, "no": 0.3, "pl": 0.21666666666666667, "pt": 0.25, "ro": 0.2, "ru": 0.3939393939393939, "sk": 0.325, "sl": 0.275, "sq": 0.1, "sr": 0.05, "stack": 0.16666666666666666, "sv": 0.35, "tr": 0.3, "uk": 0.275}}, {"model": "google/gemma-3-27b-it", "avg": 0.25368248772504093, "total": 1833, "lang_scores": {"ar": 0.3, "az": 0.15, "be": 0.225, "bg": 0.3, "bo": 0.325, "ca": 0.175, "cn": 0.3333333333333333, "cs": 0.325, "da": 0.1, "de": 0.3, "el": 0.15, "en": 0.5, "es": 0.3, "et": 0.225, "eu": 0.23333333333333334, "fa": 0.26666666666666666, "fi": 0.225, "fr": 0.2, "gl": 0.25, "hu": 0.25, "hv": 0.25, "is": 0.375, "it": 0.225, "ka": 0.175, "la": 0.36666666666666664, "li": 0.1, "lv": 0.325, "mk": 0.15, "mt": 0.225, "nl": 0.325, "no": 0.175, "pl": 0.4166666666666667, "pt": 0.25, "ro": 0.05, "ru": 0.45454545454545453, "sk": 0.2, "sl": 0.275, "sq": 0.25, "sr": 0.1, "stack": 0.2833333333333333, "sv": 0.025, "tr": 0.325, "uk": 0.325}}, {"model": "mistralai/mistral-small-3.2-24b-instruct", "avg": 0.2524972253052164, "total": 1802, "lang_scores": {"ar": 0.2, "az": 0.25, "be": 0.275, "bg": 0.225, "bo": 0.275, "ca": 0.225, "cn": 0.31666666666666665, "cs": 0.225, "da": 0.35, "de": 0.5, "el": 0.25, "en": 0.3, "es": 0.3, "et": 0.15, "eu": 0.18333333333333332, "fa": 0.3333333333333333, "fi": 0.275, "fr": 0.25, "gl": 0.16666666666666666, "hu": 0.275, "hv": 0.275, "is": 0.375, "it": 0.275, "ka": 0.2, "la": 0.4, "li": 0.20512820512820512, "lv": 0.325, "mk": 0.2, "mt": 0.1, "nl": 0.225, "no": 0.25, "pl": 0.3, "pt": 0.25, "ro": 0.2222222222222222, "ru": 0.3, "sk": 0.14285714285714285, "sl": 0.1935483870967742, "sq": 0.15789473684210525, "sr": 0.2, "stack": 0.23333333333333334, "sv": 0.3, "tr": 0.175, "uk": 0.225}}, {"model": "mistralai/mixtral-8x7b-instruct", "avg": 0.25136612021857924, "total": 1830, "lang_scores": {"ar": 0.175, "az": 0.2, "be": 0.15, "bg": 0.225, "bo": 0.25, "ca": 0.175, "cn": 0.2542372881355932, "cs": 0.4, "da": 0.25, "de": 0.5, "el": 0.2, "en": 0.3, "es": 0.3, "et": 0.275, "eu": 0.25, "fa": 0.18333333333333332, "fi": 0.275, "fr": 0.25, "gl": 0.21666666666666667, "hu": 0.25, "hv": 0.225, "is": 0.15, "it": 0.225, "ka": 0.15384615384615385, "la": 0.2833333333333333, "li": 0.2, "lv": 0.25, "mk": 0.225, "mt": 0.225, "nl": 0.3, "no": 0.325, "pl": 0.2833333333333333, "pt": 0.225, "ro": 0.3, "ru": 0.34375, "sk": 0.225, "sl": 0.325, "sq": 0.2, "sr": 0.25, "stack": 0.35, "sv": 0.225, "tr": 0.275, "uk": 0.275}}, {"model": "mistralai/mistral-7b-instruct", "avg": 0.24472049689440994, "total": 1610, "lang_scores": {"ar": 0.058823529411764705, "az": 0.2702702702702703, "be": 0.38235294117647056, "bg": 0.24324324324324326, "bo": 0.3142857142857143, "ca": 0.2857142857142857, "cn": 0.3392857142857143, "cs": 0.42857142857142855, "da": 0.28, "de": 0.25, "el": 0.19444444444444445, "en": 0.125, "es": 0.2413793103448276, "et": 0.4827586206896552, "eu": 0.22641509433962265, "fa": 0.3559322033898305, "fi": 0.2692307692307692, "fr": 0.18421052631578946, "gl": 0.20689655172413793, "hu": 0.1388888888888889, "hv": 0.3611111111111111, "is": 0.16666666666666666, "it": 0.28125, "ka": 0.2777777777777778, "la": 0.2413793103448276, "li": 0.17142857142857143, "lv": 0.14285714285714285, "mk": 0.20512820512820512, "mt": 0.16216216216216217, "nl": 0.2857142857142857, "no": 0.20512820512820512, "pl": 0.2727272727272727, "pt": 0.1891891891891892, "ro": 0.1388888888888889, "ru": 0.3548387096774194, "sk": 0.23684210526315788, "sl": 0.2894736842105263, "sq": 0.2702702702702703, "sr": 0.28205128205128205, "stack": 0.2692307692307692, "sv": 0.21052631578947367, "tr": 0.10256410256410256, "uk": 0.175}}, {"model": "CYFRAGOVPL/Llama-PLLuM-70B-chat-250801", "avg": 0.23253275109170304, "total": 1832, "lang_scores": {"ar": 0.15, "az": 0.275, "be": 0.25, "bg": 0.175, "bo": 0.25, "ca": 0.175, "cn": 0.15254237288135594, "cs": 0.225, "da": 0.175, "de": 0.5, "el": 0.225, "en": 0.225, "es": 0.125, "et": 0.25, "eu": 0.1, "fa": 0.35, "fi": 0.25, "fr": 0.225, "gl": 0.13333333333333333, "hu": 0.175, "hv": 0.375, "is": 0.4, "it": 0.2, "ka": 0.175, "la": 0.3, "li": 0.25, "lv": 0.325, "mk": 0.225, "mt": 0.275, "nl": 0.25, "no": 0.25, "pl": 0.1, "pt": 0.25, "ro": 0.25, "ru": 0.30303030303030304, "sk": 0.2, "sl": 0.175, "sq": 0.25, "sr": 0.325, "stack": 0.3, "sv": 0.25, "tr": 0.275, "uk": 0.15}}, {"model": "google/gemma-3-4b-it", "avg": 0.21941854086670323, "total": 1823, "lang_scores": {"ar": 0.1, "az": 0.15, "be": 0.225, "bg": 0.2, "bo": 0.125, "ca": 0.05128205128205128, "cn": 0.2982456140350877, "cs": 0.39473684210526316, "da": 0.25, "de": 0.0, "el": 0.175, "en": 0.425, "es": 0.225, "et": 0.375, "eu": 0.21666666666666667, "fa": 0.21666666666666667, "fi": 0.25, "fr": 0.125, "gl": 0.25, "hu": 0.125, "hv": 0.225, "is": 0.15, "it": 0.275, "ka": 0.1, "la": 0.16666666666666666, "li": 0.175, "lv": 0.2, "mk": 0.15, "mt": 0.025, "nl": 0.2, "no": 0.25, "pl": 0.31666666666666665, "pt": 0.46153846153846156, "ro": 0.125, "ru": 0.2727272727272727, "sk": 0.2631578947368421, "sl": 0.225, "sq": 0.358974358974359, "sr": 0.225, "stack": 0.21666666666666667, "sv": 0.25, "tr": 0.2, "uk": 0.275}}, {"model": "meta-llama/llama-3.1-8b-instruct", "avg": 0.21104428649535265, "total": 1829, "lang_scores": {"ar": 0.13513513513513514, "az": 0.2, "be": 0.3, "bg": 0.175, "bo": 0.2, "ca": 0.225, "cn": 0.3, "cs": 0.25, "da": 0.25, "de": 0.35, "el": 0.225, "en": 0.275, "es": 0.075, "et": 0.275, "eu": 0.11666666666666667, "fa": 0.08333333333333333, "fi": 0.3333333333333333, "fr": 0.1, "gl": 0.13333333333333333, "hu": 0.175, "hv": 0.375, "is": 0.25, "it": 0.2, "ka": 0.225, "la": 0.11666666666666667, "li": 0.2, "lv": 0.225, "mk": 0.275, "mt": 0.2, "nl": 0.225, "no": 0.225, "pl": 0.08333333333333333, "pt": 0.225, "ro": 0.075, "ru": 0.24242424242424243, "sk": 0.225, "sl": 0.25, "sq": 0.225, "sr": 0.25, "stack": 0.21666666666666667, "sv": 0.375, "tr": 0.275, "uk": 0.225}}, {"model": "mistralai/ministral-14b-2512", "avg": 0.19694489907255866, "total": 1833, "lang_scores": {"ar": 0.15, "az": 0.225, "be": 0.175, "bg": 0.2, "bo": 0.25, "ca": 0.225, "cn": 0.23333333333333334, "cs": 0.25, "da": 0.175, "de": 0.25, "el": 0.25, "en": 0.275, "es": 0.175, "et": 0.075, "eu": 0.26666666666666666, "fa": 0.21666666666666667, "fi": 0.125, "fr": 0.25, "gl": 0.21666666666666667, "hu": 0.175, "hv": 0.2, "is": 0.325, "it": 0.125, "ka": 0.05, "la": 0.4166666666666667, "li": 0.125, "lv": 0.1, "mk": 0.175, "mt": 0.05, "nl": 0.1, "no": 0.125, "pl": 0.23333333333333334, "pt": 0.15, "ro": 0.175, "ru": 0.18181818181818182, "sk": 0.175, "sl": 0.125, "sq": 0.175, "sr": 0.225, "stack": 0.2, "sv": 0.275, "tr": 0.225, "uk": 0.2}}, {"model": "mistralai/mistral-small-24b-instruct-2501", "avg": 0.18569087930092845, "total": 1831, "lang_scores": {"ar": 0.05, "az": 0.25, "be": 0.075, "bg": 0.2, "bo": 0.25, "ca": 0.25, "cn": 0.2542372881355932, "cs": 0.15, "da": 0.225, "de": 0.5, "el": 0.2, "en": 0.25, "es": 0.25, "et": 0.25, "eu": 0.2, "fa": 0.2, "fi": 0.225, "fr": 0.225, "gl": 0.18333333333333332, "hu": 0.125, "hv": 0.175, "is": 0.15, "it": 0.25, "ka": 0.025, "la": 0.35, "li": 0.05, "lv": 0.125, "mk": 0.225, "mt": 0.25, "nl": 0.175, "no": 0.225, "pl": 0.23333333333333334, "pt": 0.225, "ro": 0.1, "ru": 0.0, "sk": 0.15, "sl": 0.225, "sq": 0.025, "sr": 0.0, "stack": 0.25, "sv": 0.25, "tr": 0.075, "uk": 0.075}}, {"model": "speakleash/Bielik-11B-v2.6-Instruct", "avg": 0.15245901639344261, "total": 1830, "lang_scores": {"ar": 0.05, "az": 0.075, "be": 0.0, "bg": 0.175, "bo": 0.2, "ca": 0.175, "cn": 0.1864406779661017, "cs": 0.1, "da": 0.225, "de": 0.0, "el": 0.275, "en": 0.025, "es": 0.2, "et": 0.2, "eu": 0.16666666666666666, "fa": 0.26666666666666666, "fi": 0.125, "fr": 0.225, "gl": 0.21666666666666667, "hu": 0.2, "hv": 0.225, "is": 0.0, "it": 0.125, "ka": 0.0, "la": 0.2, "li": 0.225, "lv": 0.125, "mk": 0.2, "mt": 0.15, "nl": 0.225, "no": 0.15, "pl": 0.18333333333333332, "pt": 0.075, "ro": 0.075, "ru": 0.09090909090909091, "sk": 0.125, "sl": 0.225, "sq": 0.0, "sr": 0.05, "stack": 0.26666666666666666, "sv": 0.15, "tr": 0.225, "uk": 0.07692307692307693}}, {"model": "CYFRAGOVPL/pllum-12b-nc-chat-250715", "avg": 0.14465065502183405, "total": 1832, "lang_scores": {"ar": 0.075, "az": 0.175, "be": 0.275, "bg": 0.125, "bo": 0.325, "ca": 0.275, "cn": 0.1016949152542373, "cs": 0.075, "da": 0.125, "de": 0.15, "el": 0.175, "en": 0.15, "es": 0.2, "et": 0.075, "eu": 0.08333333333333333, "fa": 0.21666666666666667, "fi": 0.075, "fr": 0.25, "gl": 0.1, "hu": 0.025, "hv": 0.325, "is": 0.15, "it": 0.125, "ka": 0.075, "la": 0.13333333333333333, "li": 0.15, "lv": 0.1, "mk": 0.075, "mt": 0.1, "nl": 0.075, "no": 0.2, "pl": 0.11666666666666667, "pt": 0.1, "ro": 0.35, "ru": 0.21212121212121213, "sk": 0.15, "sl": 0.15, "sq": 0.075, "sr": 0.175, "stack": 0.08333333333333333, "sv": 0.125, "tr": 0.15, "uk": 0.075}}];
|
| 141 |
-
|
| 142 |
-
|
| 143 |
|
| 144 |
-
|
| 145 |
|
| 146 |
-
|
| 147 |
-
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
|
| 155 |
-
|
| 156 |
-
|
| 157 |
-
|
| 158 |
-
|
| 159 |
-
|
| 160 |
-
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
|
| 166 |
-
|
| 167 |
-
|
| 168 |
-
|
| 169 |
-
|
| 170 |
-
|
| 171 |
-
|
| 172 |
-
|
| 173 |
-
|
| 174 |
-
|
| 175 |
-
|
| 176 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 177 |
};
|
| 178 |
-
|
| 179 |
-
ALL_LANGS.forEach(l => mkChip(langName(l), l, selLangs.includes(l)));
|
| 180 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 181 |
|
| 182 |
-
|
| 183 |
-
|
| 184 |
-
|
| 185 |
-
|
| 186 |
-
|
| 187 |
-
|
| 188 |
-
|
| 189 |
-
|
| 190 |
-
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
|
| 196 |
-
|
| 197 |
-
|
| 198 |
-
|
| 199 |
-
|
| 200 |
-
|
| 201 |
-
|
| 202 |
-
|
| 203 |
-
|
| 204 |
-
|
| 205 |
-
|
| 206 |
-
|
| 207 |
-
|
| 208 |
-
|
| 209 |
-
|
| 210 |
-
|
| 211 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 212 |
};
|
| 213 |
-
|
| 214 |
-
<th class="rank-col"></th>
|
| 215 |
-
<th class="model-col"><span style="font-size:10px;text-transform:uppercase;letter-spacing:.08em;color:#475569">Model</span></th>
|
| 216 |
-
<th class="avg-col">${mkSortBtn('Avg Acc', 'avg')}</th>
|
| 217 |
-
${visLangs.map(l => `<th class="lang-col">${mkSortBtn(langName(l), l)}</th>`).join('')}
|
| 218 |
-
</tr>`;
|
| 219 |
|
| 220 |
-
|
| 221 |
-
|
| 222 |
-
|
| 223 |
-
|
| 224 |
-
|
| 225 |
-
|
| 226 |
-
|
| 227 |
-
|
| 228 |
-
|
| 229 |
-
// ββ body ββ
|
| 230 |
-
const body = document.getElementById('lb-body');
|
| 231 |
-
body.innerHTML = rows.map((row, i) => {
|
| 232 |
-
const avgPct = (row._avg * 100).toFixed(1) + '%';
|
| 233 |
-
const langCells = visLangs.map(l => {
|
| 234 |
-
const v = row._ls[l];
|
| 235 |
-
if (v === undefined) return `<td class="empty">β</td>`;
|
| 236 |
-
return `<td class="score" style="background:${scoreColor(v)};color:${textColor(v)}">${(v*100).toFixed(1)}%</td>`;
|
| 237 |
-
}).join('');
|
| 238 |
-
return `<tr>
|
| 239 |
-
<td class="rank">${i+1}</td>
|
| 240 |
-
<td class="model" title="${row.model}">${row.model}</td>
|
| 241 |
-
<td class="score" style="background:${scoreColor(row._avg)};color:${textColor(row._avg)};font-size:13px">${avgPct}</td>
|
| 242 |
-
${langCells}
|
| 243 |
-
</tr>`;
|
| 244 |
}).join('');
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 245 |
|
| 246 |
-
|
| 247 |
-
|
| 248 |
-
|
| 249 |
-
}
|
| 250 |
|
| 251 |
-
|
| 252 |
-
|
| 253 |
-
|
|
|
|
| 254 |
</body>
|
| 255 |
-
</html>
|
|
|
|
| 6 |
<title>Text Quality Rating Benchmark</title>
|
| 7 |
<link rel="preconnect" href="https://fonts.googleapis.com"/>
|
| 8 |
<link href="https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@400;600;700&family=Syne:wght@700;800&display=swap" rel="stylesheet"/>
|
| 9 |
+
<script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/4.4.1/chart.umd.min.js"></script>
|
| 10 |
<style>
|
| 11 |
*, *::before, *::after { box-sizing: border-box; margin: 0; padding: 0; }
|
| 12 |
body {
|
| 13 |
+
background: #0d1117; color: #e2e8f0;
|
|
|
|
| 14 |
font-family: 'JetBrains Mono', monospace;
|
| 15 |
+
padding: 36px 28px 80px; min-height: 100vh;
|
|
|
|
| 16 |
}
|
| 17 |
h1 {
|
| 18 |
font-family: 'Syne', sans-serif;
|
| 19 |
+
font-size: clamp(18px, 3vw, 28px); font-weight: 800;
|
| 20 |
+
letter-spacing: -0.02em; color: #f1f5f9; margin-bottom: 6px;
|
|
|
|
|
|
|
|
|
|
| 21 |
}
|
| 22 |
+
.subtitle { color: #64748b; font-size: 12px; margin-bottom: 12px; }
|
| 23 |
+
.scoring-note {
|
| 24 |
+
display: inline-flex; gap: 16px; flex-wrap: wrap;
|
| 25 |
+
background: #131820; border: 1px solid #1e2a3a;
|
| 26 |
+
border-radius: 8px; padding: 8px 14px;
|
| 27 |
+
font-size: 11px; color: #94a3b8; margin-bottom: 28px;
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
+
.scoring-note span { display: flex; align-items: center; gap: 5px; }
|
| 30 |
+
.dot { width: 9px; height: 9px; border-radius: 50%; flex-shrink: 0; }
|
| 31 |
+
|
| 32 |
+
.filter-label { font-size: 10px; text-transform: uppercase; letter-spacing: 0.1em; color: #475569; margin-bottom: 10px; }
|
| 33 |
+
#chips { display: flex; flex-wrap: wrap; gap: 6px; margin-bottom: 24px; }
|
| 34 |
.chip {
|
| 35 |
+
padding: 4px 11px; border-radius: 20px; font-size: 11px;
|
| 36 |
+
font-family: 'JetBrains Mono', monospace; cursor: pointer;
|
| 37 |
+
border: 1px solid #2d3748; background: #161b26; color: #94a3b8;
|
| 38 |
+
transition: all .15s; user-select: none;
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
}
|
| 40 |
.chip:hover { border-color: #7dd3fc; color: #e2e8f0; }
|
| 41 |
.chip.active { background: #1e3a5f; border-color: #38bdf8; color: #7dd3fc; }
|
| 42 |
+
|
| 43 |
+
.metric-toggle {
|
| 44 |
+
display: flex; width: fit-content;
|
| 45 |
+
border: 1px solid #1e2a3a; border-radius: 6px;
|
| 46 |
+
overflow: hidden; margin-bottom: 16px;
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
}
|
| 48 |
+
.mt-btn {
|
| 49 |
+
padding: 6px 14px; font: inherit; font-size: 11px; cursor: pointer;
|
| 50 |
+
border: none; background: #131820; color: #64748b; transition: all .15s;
|
| 51 |
}
|
| 52 |
+
.mt-btn.active { background: #1e3a5f; color: #7dd3fc; }
|
| 53 |
+
|
| 54 |
+
.table-wrap {
|
| 55 |
+
overflow-x: auto; border-radius: 10px;
|
| 56 |
+
border: 1px solid #1e2a3a; margin-bottom: 52px;
|
| 57 |
}
|
| 58 |
+
table { border-collapse: collapse; width: 100%; font-size: 12px; }
|
| 59 |
+
thead tr { background: #111827; border-bottom: 2px solid #1e2a3a; }
|
| 60 |
+
th { padding: 11px 6px; white-space: nowrap; }
|
| 61 |
+
th.rank-col { width: 40px; padding-left: 14px; }
|
| 62 |
+
th.model-col { text-align: left; min-width: 190px; padding-left: 14px; }
|
| 63 |
+
th.avg-col, th.lang-col { min-width: 78px; }
|
| 64 |
.sort-btn {
|
| 65 |
+
background: none; border: none; color: #64748b; cursor: pointer;
|
| 66 |
+
font: inherit; font-size: 10px; font-weight: 700;
|
| 67 |
+
text-transform: uppercase; letter-spacing: 0.07em;
|
| 68 |
+
display: inline-flex; align-items: center; gap: 3px; padding: 0; white-space: nowrap;
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
}
|
| 70 |
.sort-btn:hover { color: #7dd3fc; }
|
| 71 |
.sort-btn.active { color: #e2e8f0; }
|
| 72 |
+
tbody tr { border-bottom: 1px solid #0f1520; transition: filter .1s; }
|
|
|
|
|
|
|
|
|
|
| 73 |
tbody tr:hover { filter: brightness(1.15); }
|
| 74 |
+
td { padding: 8px 6px; white-space: nowrap; }
|
| 75 |
td.rank { padding-left: 14px; color: #475569; font-weight: 700; font-size: 13px; }
|
| 76 |
td.model { padding-left: 14px; color: #cbd5e1; font-weight: 600; max-width: 280px; overflow: hidden; text-overflow: ellipsis; }
|
| 77 |
td.score {
|
| 78 |
+
text-align: center; font-weight: 700; font-size: 11.5px;
|
|
|
|
|
|
|
| 79 |
border-right: 1px solid rgba(255,255,255,0.04);
|
| 80 |
}
|
| 81 |
+
td.empty { text-align: center; color: #2d3748; background: #111520; border-right: 1px solid rgba(255,255,255,0.04); }
|
| 82 |
+
|
| 83 |
+
.section-title {
|
| 84 |
+
font-family: 'Syne', sans-serif; font-size: 18px; font-weight: 700;
|
| 85 |
+
color: #f1f5f9; margin-bottom: 4px;
|
| 86 |
+
}
|
| 87 |
+
.chart-wrap {
|
| 88 |
+
background: #111827; border: 1px solid #1e2a3a;
|
| 89 |
+
border-radius: 10px; padding: 24px 20px;
|
| 90 |
}
|
| 91 |
+
.footer { margin-top: 20px; font-size: 11px; color: #2d3748; text-align: right; }
|
| 92 |
+
::-webkit-scrollbar { height: 5px; background: #0d1117; }
|
| 93 |
+
::-webkit-scrollbar-thumb { background: #2d3748; border-radius: 3px; }
|
| 94 |
</style>
|
| 95 |
</head>
|
| 96 |
<body>
|
| 97 |
<h1>Text Quality Rating Benchmark</h1>
|
| 98 |
+
<p class="subtitle">LLM accuracy at rating text quality on a 1β6 scale across multiple languages</p>
|
| 99 |
+
|
| 100 |
+
<div class="scoring-note">
|
| 101 |
+
<span><span class="dot" style="background:#22c55e"></span>Exact match = 1.0 pt</span>
|
| 102 |
+
<span><span class="dot" style="background:#eab308"></span>Off by Β±1 = 0.5 pt</span>
|
| 103 |
+
<span><span class="dot" style="background:#ef4444"></span>Off by β₯2 = 0.0 pt</span>
|
| 104 |
+
</div>
|
| 105 |
|
| 106 |
<div class="filter-label">Filter by language</div>
|
| 107 |
<div id="chips"></div>
|
| 108 |
|
| 109 |
+
<div class="metric-toggle">
|
| 110 |
+
<button class="mt-btn active" id="btn-wp" onclick="setMetric('wp')">Weighted Score</button>
|
| 111 |
+
<button class="mt-btn" id="btn-ex" onclick="setMetric('ex')">Exact Accuracy</button>
|
| 112 |
+
</div>
|
| 113 |
+
|
| 114 |
<div class="table-wrap">
|
| 115 |
<table id="lb-table">
|
| 116 |
<thead id="lb-head"></thead>
|
| 117 |
<tbody id="lb-body"></tbody>
|
| 118 |
</table>
|
| 119 |
</div>
|
| 120 |
+
|
| 121 |
+
<p class="section-title">Global Model Comparison</p>
|
| 122 |
+
<p class="subtitle" style="margin-bottom:20px">Weighted Score vs Exact Accuracy β all languages combined, sorted by Weighted Score</p>
|
| 123 |
+
<div class="chart-wrap">
|
| 124 |
+
<canvas id="globalChart"></canvas>
|
| 125 |
+
</div>
|
| 126 |
+
|
| 127 |
<div class="footer" id="footer"></div>
|
| 128 |
|
| 129 |
+
<script>
|
| 130 |
+
(function() {
|
| 131 |
+
const ALL_ROWS = [{"model": "Qwen/Qwen3.5-397B-A17B-FP8", "avg_exact": 0.647948, "avg_wp": 0.802783, "total": 17861, "lang_exact": {"ar": 0.675, "az": 0.7025, "be": 0.785, "bg": 0.759669, "bo": 0.735, "ca": 0.732591, "cn": 0.628333, "cs": 0.7425, "da": 0.565, "de": 0.67, "el": 0.6075, "en": 0.46, "es": 0.777778, "et": 0.6575, "eu": 0.474037, "fa": 0.565, "fi": 0.77, "fr": 0.769634, "gl": 0.521667, "hu": 0.6475, "hv": 0.7175, "is": 0.715, "it": 0.78, "ka": 0.688679, "la": 0.662768, "li": 0.6, "lv": 0.725, "mk": 0.54, "mt": 0.74, "nl": 0.58, "no": 0.695, "pl": 0.486865, "pt": 0.695, "ro": 0.625, "ru": 0.759076, "sk": 0.63, "sl": 0.715, "sq": 0.8025, "sr": 0.5625, "stack": 0.384335, "sv": 0.66, "tr": 0.55, "uk": 0.764706}, "lang_wp": {"ar": 0.8225, "az": 0.83375, "be": 0.87375, "bg": 0.870166, "bo": 0.85625, "ca": 0.85376, "cn": 0.7875, "cs": 0.85125, "da": 0.77125, "de": 0.8225, "el": 0.79625, "en": 0.71125, "es": 0.876877, "et": 0.8175, "eu": 0.68593, "fa": 0.758333, "fi": 0.87125, "fr": 0.870419, "gl": 0.721667, "hu": 0.79625, "hv": 0.85625, "is": 0.8475, "it": 0.87875, "ka": 0.794025, "la": 0.798246, "li": 0.78875, "lv": 0.85625, "mk": 0.75125, "mt": 0.8475, "nl": 0.78, "no": 0.8075, "pl": 0.707531, "pt": 0.80625, "ro": 0.7825, "ru": 0.866337, "sk": 0.8, "sl": 0.85, "sq": 0.89375, "sr": 0.77375, "stack": 0.625683, "sv": 0.82125, "tr": 0.755, "uk": 0.874332}}, {"model": "google/gemini-3-flash-preview", "avg_exact": 0.57665, "avg_wp": 0.759956, "total": 1833, "lang_exact": {"ar": 0.575, "az": 0.55, "be": 0.625, "bg": 0.75, "bo": 0.575, "ca": 0.725, "cn": 0.566667, "cs": 0.525, "da": 0.475, "de": 0.65, "el": 0.575, "en": 0.4, "es": 0.825, "et": 0.625, "eu": 0.416667, "fa": 0.516667, "fi": 0.625, "fr": 0.675, "gl": 0.533333, "hu": 0.575, "hv": 0.7, "is": 0.55, "it": 0.725, "ka": 0.6, "la": 0.5, "li": 0.5, "lv": 0.6, "mk": 0.525, "mt": 0.7, "nl": 0.45, "no": 0.6, "pl": 0.366667, "pt": 0.525, "ro": 0.625, "ru": 0.69697, "sk": 0.525, "sl": 0.7, "sq": 0.675, "sr": 0.475, "stack": 0.533333, "sv": 0.6, "tr": 0.6, "uk": 0.6}, "lang_wp": {"ar": 0.7875, "az": 0.6875, "be": 0.8125, "bg": 0.8625, "bo": 0.775, "ca": 0.8375, "cn": 0.783333, "cs": 0.725, "da": 0.725, "de": 0.775, "el": 0.775, "en": 0.65, "es": 0.9125, "et": 0.8125, "eu": 0.608333, "fa": 0.725, "fi": 0.775, "fr": 0.8125, "gl": 0.7, "hu": 0.7875, "hv": 0.85, "is": 0.7125, "it": 0.85, "ka": 0.8, "la": 0.658333, "li": 0.725, "lv": 0.7875, "mk": 0.7125, "mt": 0.8, "nl": 0.7, "no": 0.775, "pl": 0.641667, "pt": 0.75, "ro": 0.75, "ru": 0.833333, "sk": 0.7625, "sl": 0.8375, "sq": 0.825, "sr": 0.7375, "stack": 0.741667, "sv": 0.8, "tr": 0.7625, "uk": 0.7875}}, {"model": "openai/gpt-4o-mini", "avg_exact": 0.587978, "avg_wp": 0.751639, "total": 1830, "lang_exact": {"ar": 0.615385, "az": 0.5, "be": 0.725, "bg": 0.675, "bo": 0.675, "ca": 0.475, "cn": 0.7, "cs": 0.6, "da": 0.525, "de": 0.55, "el": 0.525, "en": 0.425, "es": 0.8, "et": 0.875, "eu": 0.35, "fa": 0.533333, "fi": 0.65, "fr": 0.575, "gl": 0.433333, "hu": 0.65, "hv": 0.7, "is": 0.6, "it": 0.725, "ka": 0.475, "la": 0.4, "li": 0.675, "lv": 0.725, "mk": 0.4, "mt": 0.6, "nl": 0.475, "no": 0.675, "pl": 0.383333, "pt": 0.75, "ro": 0.5, "ru": 0.848485, "sk": 0.7, "sl": 0.7, "sq": 0.7, "sr": 0.475, "stack": 0.366667, "sv": 0.725, "tr": 0.65, "uk": 0.684211}, "lang_wp": {"ar": 0.782051, "az": 0.725, "be": 0.8625, "bg": 0.8125, "bo": 0.8375, "ca": 0.675, "cn": 0.841667, "cs": 0.7625, "da": 0.725, "de": 0.75, "el": 0.7375, "en": 0.5875, "es": 0.9, "et": 0.9375, "eu": 0.583333, "fa": 0.733333, "fi": 0.775, "fr": 0.7625, "gl": 0.666667, "hu": 0.8125, "hv": 0.825, "is": 0.7875, "it": 0.8375, "ka": 0.6625, "la": 0.566667, "li": 0.8125, "lv": 0.8625, "mk": 0.575, "mt": 0.7875, "nl": 0.7, "no": 0.7875, "pl": 0.566667, "pt": 0.8625, "ro": 0.7, "ru": 0.893939, "sk": 0.825, "sl": 0.8375, "sq": 0.825, "sr": 0.6875, "stack": 0.575, "sv": 0.8375, "tr": 0.8, "uk": 0.828947}}, {"model": "qwen/qwen3-235b-a22b-2507", "avg_exact": 0.493181, "avg_wp": 0.693126, "total": 1833, "lang_exact": {"ar": 0.6, "az": 0.475, "be": 0.55, "bg": 0.65, "bo": 0.55, "ca": 0.525, "cn": 0.433333, "cs": 0.425, "da": 0.45, "de": 0.65, "el": 0.55, "en": 0.425, "es": 0.525, "et": 0.5, "eu": 0.416667, "fa": 0.616667, "fi": 0.55, "fr": 0.6, "gl": 0.433333, "hu": 0.65, "hv": 0.625, "is": 0.475, "it": 0.65, "ka": 0.325, "la": 0.433333, "li": 0.4, "lv": 0.575, "mk": 0.35, "mt": 0.475, "nl": 0.35, "no": 0.4, "pl": 0.316667, "pt": 0.575, "ro": 0.5, "ru": 0.454545, "sk": 0.45, "sl": 0.575, "sq": 0.6, "sr": 0.5, "stack": 0.35, "sv": 0.475, "tr": 0.45, "uk": 0.625}, "lang_wp": {"ar": 0.775, "az": 0.7, "be": 0.75, "bg": 0.8, "bo": 0.75, "ca": 0.7, "cn": 0.616667, "cs": 0.6375, "da": 0.6625, "de": 0.8, "el": 0.725, "en": 0.55, "es": 0.725, "et": 0.75, "eu": 0.608333, "fa": 0.783333, "fi": 0.725, "fr": 0.7625, "gl": 0.625, "hu": 0.8125, "hv": 0.8, "is": 0.7, "it": 0.8125, "ka": 0.6, "la": 0.558333, "li": 0.6625, "lv": 0.775, "mk": 0.575, "mt": 0.675, "nl": 0.6, "no": 0.65, "pl": 0.458333, "pt": 0.775, "ro": 0.7375, "ru": 0.712121, "sk": 0.7, "sl": 0.775, "sq": 0.7625, "sr": 0.725, "stack": 0.633333, "sv": 0.725, "tr": 0.675, "uk": 0.8}}, {"model": "deepseek/deepseek-v3.2", "avg_exact": 0.406438, "avg_wp": 0.632024, "total": 1833, "lang_exact": {"ar": 0.375, "az": 0.325, "be": 0.475, "bg": 0.475, "bo": 0.475, "ca": 0.425, "cn": 0.533333, "cs": 0.5, "da": 0.275, "de": 0.6, "el": 0.25, "en": 0.525, "es": 0.425, "et": 0.425, "eu": 0.333333, "fa": 0.35, "fi": 0.375, "fr": 0.45, "gl": 0.483333, "hu": 0.4, "hv": 0.475, "is": 0.575, "it": 0.425, "ka": 0.35, "la": 0.3, "li": 0.375, "lv": 0.4, "mk": 0.325, "mt": 0.375, "nl": 0.325, "no": 0.4, "pl": 0.366667, "pt": 0.475, "ro": 0.25, "ru": 0.484848, "sk": 0.375, "sl": 0.6, "sq": 0.375, "sr": 0.3, "stack": 0.416667, "sv": 0.375, "tr": 0.375, "uk": 0.425}, "lang_wp": {"ar": 0.625, "az": 0.5625, "be": 0.725, "bg": 0.675, "bo": 0.7, "ca": 0.6375, "cn": 0.741667, "cs": 0.6875, "da": 0.5125, "de": 0.725, "el": 0.475, "en": 0.6875, "es": 0.7, "et": 0.7, "eu": 0.541667, "fa": 0.633333, "fi": 0.5875, "fr": 0.6875, "gl": 0.683333, "hu": 0.65, "hv": 0.7125, "is": 0.7625, "it": 0.6875, "ka": 0.575, "la": 0.5, "li": 0.5375, "lv": 0.6625, "mk": 0.55, "mt": 0.5625, "nl": 0.5625, "no": 0.625, "pl": 0.558333, "pt": 0.7, "ro": 0.4625, "ru": 0.712121, "sk": 0.625, "sl": 0.775, "sq": 0.6625, "sr": 0.6, "stack": 0.675, "sv": 0.6, "tr": 0.625, "uk": 0.6125}}, {"model": "z-ai/glm-4-32b", "avg_exact": 0.424986, "avg_wp": 0.613748, "total": 1833, "lang_exact": {"ar": 0.375, "az": 0.5, "be": 0.625, "bg": 0.375, "bo": 0.625, "ca": 0.35, "cn": 0.383333, "cs": 0.625, "da": 0.35, "de": 0.4, "el": 0.55, "en": 0.3, "es": 0.35, "et": 0.525, "eu": 0.3, "fa": 0.383333, "fi": 0.525, "fr": 0.525, "gl": 0.25, "hu": 0.5, "hv": 0.625, "is": 0.35, "it": 0.4, "ka": 0.5, "la": 0.433333, "li": 0.425, "lv": 0.525, "mk": 0.225, "mt": 0.35, "nl": 0.425, "no": 0.475, "pl": 0.35, "pt": 0.25, "ro": 0.3, "ru": 0.515152, "sk": 0.525, "sl": 0.475, "sq": 0.7, "sr": 0.375, "stack": 0.216667, "sv": 0.4, "tr": 0.425, "uk": 0.525}, "lang_wp": {"ar": 0.525, "az": 0.7, "be": 0.775, "bg": 0.5375, "bo": 0.7625, "ca": 0.5, "cn": 0.583333, "cs": 0.775, "da": 0.6, "de": 0.45, "el": 0.7375, "en": 0.45, "es": 0.575, "et": 0.725, "eu": 0.533333, "fa": 0.608333, "fi": 0.6375, "fr": 0.6625, "gl": 0.375, "hu": 0.65, "hv": 0.8125, "is": 0.5875, "it": 0.6, "ka": 0.65, "la": 0.558333, "li": 0.65, "lv": 0.7125, "mk": 0.4125, "mt": 0.5625, "nl": 0.675, "no": 0.675, "pl": 0.575, "pt": 0.4375, "ro": 0.525, "ru": 0.69697, "sk": 0.7375, "sl": 0.6875, "sq": 0.8375, "sr": 0.6, "stack": 0.458333, "sv": 0.625, "tr": 0.675, "uk": 0.7125}}, {"model": "speakleash/Bielik-11B-v3.0-Instruct", "avg_exact": 0.417804, "avg_wp": 0.605407, "total": 1831, "lang_exact": {"ar": 0.025, "az": 0.525, "be": 0.2, "bg": 0.525, "bo": 0.675, "ca": 0.325, "cn": 0.271186, "cs": 0.5, "da": 0.425, "de": 0.95, "el": 0.325, "en": 0.5, "es": 0.475, "et": 0.55, "eu": 0.25, "fa": 0.366667, "fi": 0.425, "fr": 0.5, "gl": 0.4, "hu": 0.475, "hv": 0.525, "is": 0.225, "it": 0.475, "ka": 0.230769, "la": 0.3, "li": 0.45, "lv": 0.425, "mk": 0.275, "mt": 0.375, "nl": 0.45, "no": 0.475, "pl": 0.366667, "pt": 0.475, "ro": 0.425, "ru": 0.606061, "sk": 0.475, "sl": 0.55, "sq": 0.5, "sr": 0.45, "stack": 0.333333, "sv": 0.425, "tr": 0.45, "uk": 0.625}, "lang_wp": {"ar": 0.15, "az": 0.6875, "be": 0.275, "bg": 0.675, "bo": 0.7875, "ca": 0.6125, "cn": 0.40678, "cs": 0.6125, "da": 0.675, "de": 0.975, "el": 0.5625, "en": 0.65, "es": 0.7125, "et": 0.7375, "eu": 0.483333, "fa": 0.583333, "fi": 0.5375, "fr": 0.725, "gl": 0.608333, "hu": 0.6625, "hv": 0.675, "is": 0.3875, "it": 0.6875, "ka": 0.371795, "la": 0.483333, "li": 0.675, "lv": 0.675, "mk": 0.575, "mt": 0.575, "nl": 0.7125, "no": 0.6875, "pl": 0.541667, "pt": 0.6875, "ro": 0.65, "ru": 0.727273, "sk": 0.6125, "sl": 0.6625, "sq": 0.6625, "sr": 0.6, "stack": 0.583333, "sv": 0.7, "tr": 0.7, "uk": 0.75}}, {"model": "google/gemini-2.0-flash-lite-001", "avg_exact": 0.37916, "avg_wp": 0.58347, "total": 1833, "lang_exact": {"ar": 0.325, "az": 0.325, "be": 0.55, "bg": 0.6, "bo": 0.4, "ca": 0.275, "cn": 0.45, "cs": 0.3, "da": 0.4, "de": 0.35, "el": 0.225, "en": 0.525, "es": 0.4, "et": 0.55, "eu": 0.333333, "fa": 0.516667, "fi": 0.4, "fr": 0.425, "gl": 0.383333, "hu": 0.45, "hv": 0.425, "is": 0.2, "it": 0.425, "ka": 0.3, "la": 0.216667, "li": 0.425, "lv": 0.475, "mk": 0.2, "mt": 0.425, "nl": 0.4, "no": 0.325, "pl": 0.366667, "pt": 0.375, "ro": 0.275, "ru": 0.606061, "sk": 0.425, "sl": 0.375, "sq": 0.425, "sr": 0.25, "stack": 0.216667, "sv": 0.425, "tr": 0.4, "uk": 0.275}, "lang_wp": {"ar": 0.525, "az": 0.6, "be": 0.75, "bg": 0.7625, "bo": 0.5875, "ca": 0.525, "cn": 0.608333, "cs": 0.5, "da": 0.55, "de": 0.6, "el": 0.5, "en": 0.7125, "es": 0.65, "et": 0.6875, "eu": 0.566667, "fa": 0.691667, "fi": 0.6375, "fr": 0.6125, "gl": 0.633333, "hu": 0.6375, "hv": 0.625, "is": 0.45, "it": 0.6125, "ka": 0.525, "la": 0.383333, "li": 0.575, "lv": 0.7, "mk": 0.4625, "mt": 0.65, "nl": 0.6125, "no": 0.4875, "pl": 0.55, "pt": 0.525, "ro": 0.4375, "ru": 0.712121, "sk": 0.6, "sl": 0.6125, "sq": 0.6125, "sr": 0.4875, "stack": 0.491667, "sv": 0.6375, "tr": 0.5875, "uk": 0.525}}, {"model": "google/gemma-3-12b-it", "avg_exact": 0.337152, "avg_wp": 0.569285, "total": 1833, "lang_exact": {"ar": 0.275, "az": 0.35, "be": 0.35, "bg": 0.475, "bo": 0.45, "ca": 0.225, "cn": 0.383333, "cs": 0.45, "da": 0.375, "de": 0.5, "el": 0.275, "en": 0.45, "es": 0.325, "et": 0.4, "eu": 0.233333, "fa": 0.25, "fi": 0.4, "fr": 0.425, "gl": 0.166667, "hu": 0.35, "hv": 0.4, "is": 0.475, "it": 0.325, "ka": 0.3, "la": 0.3, "li": 0.25, "lv": 0.425, "mk": 0.275, "mt": 0.25, "nl": 0.45, "no": 0.375, "pl": 0.366667, "pt": 0.25, "ro": 0.25, "ru": 0.575758, "sk": 0.275, "sl": 0.35, "sq": 0.35, "sr": 0.325, "stack": 0.266667, "sv": 0.175, "tr": 0.325, "uk": 0.375}, "lang_wp": {"ar": 0.5, "az": 0.625, "be": 0.6125, "bg": 0.6625, "bo": 0.675, "ca": 0.4875, "cn": 0.583333, "cs": 0.625, "da": 0.5875, "de": 0.6, "el": 0.5125, "en": 0.5625, "es": 0.5875, "et": 0.625, "eu": 0.466667, "fa": 0.533333, "fi": 0.625, "fr": 0.675, "gl": 0.375, "hu": 0.6125, "hv": 0.6375, "is": 0.6875, "it": 0.5375, "ka": 0.475, "la": 0.525, "li": 0.5875, "lv": 0.6625, "mk": 0.55, "mt": 0.5375, "nl": 0.725, "no": 0.5625, "pl": 0.575, "pt": 0.525, "ro": 0.4875, "ru": 0.787879, "sk": 0.5625, "sl": 0.6, "sq": 0.5125, "sr": 0.5875, "stack": 0.425, "sv": 0.5125, "tr": 0.6125, "uk": 0.575}}, {"model": "mistralai/mistral-nemo", "avg_exact": 0.310966, "avg_wp": 0.503273, "total": 1833, "lang_exact": {"ar": 0.325, "az": 0.45, "be": 0.475, "bg": 0.325, "bo": 0.375, "ca": 0.25, "cn": 0.383333, "cs": 0.425, "da": 0.375, "de": 0.4, "el": 0.3, "en": 0.25, "es": 0.35, "et": 0.225, "eu": 0.216667, "fa": 0.266667, "fi": 0.35, "fr": 0.275, "gl": 0.283333, "hu": 0.2, "hv": 0.425, "is": 0.3, "it": 0.2, "ka": 0.425, "la": 0.183333, "li": 0.325, "lv": 0.425, "mk": 0.375, "mt": 0.325, "nl": 0.35, "no": 0.375, "pl": 0.25, "pt": 0.35, "ro": 0.2, "ru": 0.212121, "sk": 0.375, "sl": 0.35, "sq": 0.3, "sr": 0.25, "stack": 0.333333, "sv": 0.175, "tr": 0.275, "uk": 0.25}, "lang_wp": {"ar": 0.5, "az": 0.6125, "be": 0.675, "bg": 0.4625, "bo": 0.5, "ca": 0.5125, "cn": 0.608333, "cs": 0.5125, "da": 0.5375, "de": 0.575, "el": 0.4625, "en": 0.5, "es": 0.575, "et": 0.4875, "eu": 0.441667, "fa": 0.5, "fi": 0.525, "fr": 0.5625, "gl": 0.475, "hu": 0.425, "hv": 0.5875, "is": 0.4625, "it": 0.4, "ka": 0.5875, "la": 0.333333, "li": 0.525, "lv": 0.6625, "mk": 0.5375, "mt": 0.425, "nl": 0.4875, "no": 0.5375, "pl": 0.466667, "pt": 0.525, "ro": 0.3, "ru": 0.484848, "sk": 0.6, "sl": 0.575, "sq": 0.425, "sr": 0.45, "stack": 0.583333, "sv": 0.4375, "tr": 0.45, "uk": 0.4375}}, {"model": "z-ai/glm-4.5-air", "avg_exact": 0.362248, "avg_wp": 0.503273, "total": 1833, "lang_exact": {"ar": 0.325, "az": 0.4, "be": 0.525, "bg": 0.475, "bo": 0.45, "ca": 0.375, "cn": 0.4, "cs": 0.35, "da": 0.325, "de": 0.4, "el": 0.325, "en": 0.275, "es": 0.35, "et": 0.6, "eu": 0.3, "fa": 0.283333, "fi": 0.45, "fr": 0.3, "gl": 0.383333, "hu": 0.375, "hv": 0.175, "is": 0.25, "it": 0.125, "ka": 0.35, "la": 0.15, "li": 0.175, "lv": 0.1, "mk": 0.2, "mt": 0.275, "nl": 0.225, "no": 0.375, "pl": 0.35, "pt": 0.525, "ro": 0.4, "ru": 0.484848, "sk": 0.55, "sl": 0.625, "sq": 0.65, "sr": 0.325, "stack": 0.35, "sv": 0.5, "tr": 0.45, "uk": 0.5}, "lang_wp": {"ar": 0.5375, "az": 0.55, "be": 0.6375, "bg": 0.6375, "bo": 0.575, "ca": 0.475, "cn": 0.6, "cs": 0.5, "da": 0.4875, "de": 0.525, "el": 0.5125, "en": 0.4375, "es": 0.5, "et": 0.75, "eu": 0.433333, "fa": 0.525, "fi": 0.5125, "fr": 0.475, "gl": 0.541667, "hu": 0.425, "hv": 0.1875, "is": 0.3625, "it": 0.15, "ka": 0.4125, "la": 0.208333, "li": 0.25, "lv": 0.2, "mk": 0.3375, "mt": 0.4375, "nl": 0.375, "no": 0.5125, "pl": 0.5, "pt": 0.6625, "ro": 0.5375, "ru": 0.621212, "sk": 0.7, "sl": 0.775, "sq": 0.75, "sr": 0.55, "stack": 0.625, "sv": 0.625, "tr": 0.6375, "uk": 0.6625}}, {"model": "meta-llama/llama-3.3-70b-instruct", "avg_exact": 0.366962, "avg_wp": 0.500554, "total": 1804, "lang_exact": {"ar": 0.384615, "az": 0.394737, "be": 0.475, "bg": 0.4, "bo": 0.45, "ca": 0.25, "cn": 0.305085, "cs": 0.525, "da": 0.358974, "de": 0.45, "el": 0.447368, "en": 0.25641, "es": 0.324324, "et": 0.512821, "eu": 0.293103, "fa": 0.310345, "fi": 0.538462, "fr": 0.384615, "gl": 0.183333, "hu": 0.45, "hv": 0.4, "is": 0.45, "it": 0.384615, "ka": 0.35, "la": 0.310345, "li": 0.25641, "lv": 0.425, "mk": 0.225, "mt": 0.275, "nl": 0.425, "no": 0.375, "pl": 0.4, "pt": 0.358974, "ro": 0.131579, "ru": 0.515152, "sk": 0.425, "sl": 0.435897, "sq": 0.282051, "sr": 0.333333, "stack": 0.35, "sv": 0.410256, "tr": 0.475, "uk": 0.35}, "lang_wp": {"ar": 0.5, "az": 0.513158, "be": 0.5625, "bg": 0.5375, "bo": 0.5375, "ca": 0.3625, "cn": 0.466102, "cs": 0.5875, "da": 0.5, "de": 0.575, "el": 0.5, "en": 0.435897, "es": 0.405405, "et": 0.679487, "eu": 0.431034, "fa": 0.465517, "fi": 0.653846, "fr": 0.448718, "gl": 0.383333, "hu": 0.5375, "hv": 0.5125, "is": 0.625, "it": 0.512821, "ka": 0.4625, "la": 0.431034, "li": 0.423077, "lv": 0.6, "mk": 0.3625, "mt": 0.3875, "nl": 0.5875, "no": 0.475, "pl": 0.558333, "pt": 0.474359, "ro": 0.315789, "ru": 0.530303, "sk": 0.6375, "sl": 0.551282, "sq": 0.487179, "sr": 0.448718, "stack": 0.591667, "sv": 0.512821, "tr": 0.625, "uk": 0.4375}}, {"model": "meta-llama/llama-4-scout", "avg_exact": 0.376843, "avg_wp": 0.495904, "total": 1831, "lang_exact": {"ar": 0.325, "az": 0.475, "be": 0.3, "bg": 0.375, "bo": 0.425, "ca": 0.3, "cn": 0.25, "cs": 0.525, "da": 0.375, "de": 0.6, "el": 0.275, "en": 0.225, "es": 0.475, "et": 0.425, "eu": 0.254237, "fa": 0.4, "fi": 0.5, "fr": 0.375, "gl": 0.2, "hu": 0.45, "hv": 0.45, "is": 0.55, "it": 0.425, "ka": 0.3, "la": 0.316667, "li": 0.35, "lv": 0.45, "mk": 0.275, "mt": 0.35, "nl": 0.325, "no": 0.475, "pl": 0.35, "pt": 0.5, "ro": 0.325, "ru": 0.545455, "sk": 0.5, "sl": 0.4, "sq": 0.575, "sr": 0.275, "stack": 0.216667, "sv": 0.425, "tr": 0.425, "uk": 0.333333}, "lang_wp": {"ar": 0.4625, "az": 0.5625, "be": 0.4, "bg": 0.45, "bo": 0.5375, "ca": 0.3875, "cn": 0.441667, "cs": 0.6, "da": 0.4875, "de": 0.625, "el": 0.4, "en": 0.325, "es": 0.5875, "et": 0.5875, "eu": 0.389831, "fa": 0.55, "fi": 0.625, "fr": 0.4375, "gl": 0.433333, "hu": 0.5375, "hv": 0.525, "is": 0.65, "it": 0.4625, "ka": 0.4125, "la": 0.425, "li": 0.45, "lv": 0.575, "mk": 0.425, "mt": 0.5125, "nl": 0.475, "no": 0.6125, "pl": 0.441667, "pt": 0.6, "ro": 0.475, "ru": 0.575758, "sk": 0.55, "sl": 0.525, "sq": 0.6625, "sr": 0.4125, "stack": 0.408333, "sv": 0.5375, "tr": 0.6, "uk": 0.448718}}, {"model": "openai/gpt-4.1-nano", "avg_exact": 0.289847, "avg_wp": 0.494814, "total": 1832, "lang_exact": {"ar": 0.25641, "az": 0.275, "be": 0.25, "bg": 0.35, "bo": 0.325, "ca": 0.125, "cn": 0.4, "cs": 0.35, "da": 0.375, "de": 0.0, "el": 0.225, "en": 0.1, "es": 0.275, "et": 0.45, "eu": 0.2, "fa": 0.366667, "fi": 0.5, "fr": 0.325, "gl": 0.3, "hu": 0.25, "hv": 0.35, "is": 0.3, "it": 0.3, "ka": 0.125, "la": 0.2, "li": 0.275, "lv": 0.425, "mk": 0.125, "mt": 0.25, "nl": 0.3, "no": 0.275, "pl": 0.3, "pt": 0.225, "ro": 0.25, "ru": 0.393939, "sk": 0.275, "sl": 0.3, "sq": 0.325, "sr": 0.325, "stack": 0.283333, "sv": 0.375, "tr": 0.325, "uk": 0.325}, "lang_wp": {"ar": 0.5, "az": 0.5125, "be": 0.4875, "bg": 0.55, "bo": 0.525, "ca": 0.4, "cn": 0.616667, "cs": 0.55, "da": 0.425, "de": 0.45, "el": 0.475, "en": 0.4125, "es": 0.4625, "et": 0.6125, "eu": 0.391667, "fa": 0.6, "fi": 0.6, "fr": 0.5125, "gl": 0.5, "hu": 0.475, "hv": 0.5375, "is": 0.55, "it": 0.5125, "ka": 0.3125, "la": 0.316667, "li": 0.5375, "lv": 0.6125, "mk": 0.3125, "mt": 0.3875, "nl": 0.4125, "no": 0.425, "pl": 0.541667, "pt": 0.425, "ro": 0.4625, "ru": 0.651515, "sk": 0.4625, "sl": 0.575, "sq": 0.5625, "sr": 0.5375, "stack": 0.525, "sv": 0.5, "tr": 0.4875, "uk": 0.5625}}, {"model": "google/gemma-3-27b-it", "avg_exact": 0.253682, "avg_wp": 0.490726, "total": 1833, "lang_exact": {"ar": 0.3, "az": 0.15, "be": 0.225, "bg": 0.3, "bo": 0.325, "ca": 0.175, "cn": 0.333333, "cs": 0.325, "da": 0.1, "de": 0.3, "el": 0.15, "en": 0.5, "es": 0.3, "et": 0.225, "eu": 0.233333, "fa": 0.266667, "fi": 0.225, "fr": 0.2, "gl": 0.25, "hu": 0.25, "hv": 0.25, "is": 0.375, "it": 0.225, "ka": 0.175, "la": 0.366667, "li": 0.1, "lv": 0.325, "mk": 0.15, "mt": 0.225, "nl": 0.325, "no": 0.175, "pl": 0.416667, "pt": 0.25, "ro": 0.05, "ru": 0.454545, "sk": 0.2, "sl": 0.275, "sq": 0.25, "sr": 0.1, "stack": 0.283333, "sv": 0.025, "tr": 0.325, "uk": 0.325}, "lang_wp": {"ar": 0.4875, "az": 0.4, "be": 0.4625, "bg": 0.4875, "bo": 0.5875, "ca": 0.4, "cn": 0.575, "cs": 0.4625, "da": 0.375, "de": 0.45, "el": 0.325, "en": 0.65, "es": 0.5125, "et": 0.5125, "eu": 0.475, "fa": 0.55, "fi": 0.475, "fr": 0.475, "gl": 0.466667, "hu": 0.55, "hv": 0.5, "is": 0.5625, "it": 0.4875, "ka": 0.375, "la": 0.525, "li": 0.4125, "lv": 0.5875, "mk": 0.275, "mt": 0.5125, "nl": 0.5875, "no": 0.3875, "pl": 0.591667, "pt": 0.4625, "ro": 0.35, "ru": 0.666667, "sk": 0.5375, "sl": 0.5125, "sq": 0.475, "sr": 0.4125, "stack": 0.566667, "sv": 0.3625, "tr": 0.5625, "uk": 0.5625}}, {"model": "qwen/qwen-2.5-7b-instruct", "avg_exact": 0.261866, "avg_wp": 0.484452, "total": 1833, "lang_exact": {"ar": 0.2, "az": 0.15, "be": 0.25, "bg": 0.35, "bo": 0.4, "ca": 0.225, "cn": 0.316667, "cs": 0.3, "da": 0.325, "de": 0.25, "el": 0.2, "en": 0.4, "es": 0.325, "et": 0.25, "eu": 0.216667, "fa": 0.3, "fi": 0.275, "fr": 0.35, "gl": 0.366667, "hu": 0.225, "hv": 0.3, "is": 0.325, "it": 0.3, "ka": 0.125, "la": 0.183333, "li": 0.2, "lv": 0.35, "mk": 0.15, "mt": 0.225, "nl": 0.275, "no": 0.3, "pl": 0.216667, "pt": 0.25, "ro": 0.2, "ru": 0.393939, "sk": 0.325, "sl": 0.275, "sq": 0.1, "sr": 0.05, "stack": 0.166667, "sv": 0.35, "tr": 0.3, "uk": 0.275}, "lang_wp": {"ar": 0.3625, "az": 0.4, "be": 0.5125, "bg": 0.575, "bo": 0.625, "ca": 0.425, "cn": 0.525, "cs": 0.4875, "da": 0.525, "de": 0.475, "el": 0.425, "en": 0.6125, "es": 0.5625, "et": 0.5, "eu": 0.425, "fa": 0.466667, "fi": 0.5125, "fr": 0.5375, "gl": 0.566667, "hu": 0.475, "hv": 0.525, "is": 0.5125, "it": 0.5, "ka": 0.3125, "la": 0.383333, "li": 0.3875, "lv": 0.65, "mk": 0.3375, "mt": 0.4125, "nl": 0.525, "no": 0.5125, "pl": 0.425, "pt": 0.475, "ro": 0.4125, "ru": 0.621212, "sk": 0.5625, "sl": 0.5, "sq": 0.35, "sr": 0.35, "stack": 0.483333, "sv": 0.6, "tr": 0.5625, "uk": 0.5125}}, {"model": "mistralai/mixtral-8x7b-instruct", "avg_exact": 0.251366, "avg_wp": 0.457104, "total": 1830, "lang_exact": {"ar": 0.175, "az": 0.2, "be": 0.15, "bg": 0.225, "bo": 0.25, "ca": 0.175, "cn": 0.254237, "cs": 0.4, "da": 0.25, "de": 0.5, "el": 0.2, "en": 0.3, "es": 0.3, "et": 0.275, "eu": 0.25, "fa": 0.183333, "fi": 0.275, "fr": 0.25, "gl": 0.216667, "hu": 0.25, "hv": 0.225, "is": 0.15, "it": 0.225, "ka": 0.153846, "la": 0.283333, "li": 0.2, "lv": 0.25, "mk": 0.225, "mt": 0.225, "nl": 0.3, "no": 0.325, "pl": 0.283333, "pt": 0.225, "ro": 0.3, "ru": 0.34375, "sk": 0.225, "sl": 0.325, "sq": 0.2, "sr": 0.25, "stack": 0.35, "sv": 0.225, "tr": 0.275, "uk": 0.275}, "lang_wp": {"ar": 0.2875, "az": 0.3875, "be": 0.45, "bg": 0.4375, "bo": 0.425, "ca": 0.3375, "cn": 0.466102, "cs": 0.5625, "da": 0.5125, "de": 0.5, "el": 0.4, "en": 0.5125, "es": 0.5125, "et": 0.4875, "eu": 0.408333, "fa": 0.408333, "fi": 0.525, "fr": 0.4125, "gl": 0.408333, "hu": 0.4875, "hv": 0.475, "is": 0.4, "it": 0.4125, "ka": 0.269231, "la": 0.466667, "li": 0.4375, "lv": 0.5, "mk": 0.3875, "mt": 0.3625, "nl": 0.5625, "no": 0.55, "pl": 0.45, "pt": 0.475, "ro": 0.525, "ru": 0.53125, "sk": 0.4625, "sl": 0.5, "sq": 0.4, "sr": 0.475, "stack": 0.55, "sv": 0.55, "tr": 0.4875, "uk": 0.55}}, {"model": "google/gemma-3-4b-it", "avg_exact": 0.219419, "avg_wp": 0.455293, "total": 1823, "lang_exact": {"ar": 0.1, "az": 0.15, "be": 0.225, "bg": 0.2, "bo": 0.125, "ca": 0.051282, "cn": 0.298246, "cs": 0.394737, "da": 0.25, "de": 0.0, "el": 0.175, "en": 0.425, "es": 0.225, "et": 0.375, "eu": 0.216667, "fa": 0.216667, "fi": 0.25, "fr": 0.125, "gl": 0.25, "hu": 0.125, "hv": 0.225, "is": 0.15, "it": 0.275, "ka": 0.1, "la": 0.166667, "li": 0.175, "lv": 0.2, "mk": 0.15, "mt": 0.025, "nl": 0.2, "no": 0.25, "pl": 0.316667, "pt": 0.461538, "ro": 0.125, "ru": 0.272727, "sk": 0.263158, "sl": 0.225, "sq": 0.358974, "sr": 0.225, "stack": 0.216667, "sv": 0.25, "tr": 0.2, "uk": 0.275}, "lang_wp": {"ar": 0.425, "az": 0.5, "be": 0.5, "bg": 0.4125, "bo": 0.45, "ca": 0.294872, "cn": 0.54386, "cs": 0.539474, "da": 0.45, "de": 0.225, "el": 0.375, "en": 0.6375, "es": 0.425, "et": 0.5875, "eu": 0.441667, "fa": 0.45, "fi": 0.525, "fr": 0.35, "gl": 0.541667, "hu": 0.4, "hv": 0.475, "is": 0.375, "it": 0.4875, "ka": 0.325, "la": 0.35, "li": 0.4875, "lv": 0.525, "mk": 0.3625, "mt": 0.325, "nl": 0.4375, "no": 0.475, "pl": 0.516667, "pt": 0.615385, "ro": 0.3375, "ru": 0.545455, "sk": 0.526316, "sl": 0.425, "sq": 0.538462, "sr": 0.4875, "stack": 0.391667, "sv": 0.5, "tr": 0.4375, "uk": 0.45}}, {"model": "mistralai/mistral-small-3.2-24b-instruct", "avg_exact": 0.252497, "avg_wp": 0.451998, "total": 1802, "lang_exact": {"ar": 0.2, "az": 0.25, "be": 0.275, "bg": 0.225, "bo": 0.275, "ca": 0.225, "cn": 0.316667, "cs": 0.225, "da": 0.35, "de": 0.5, "el": 0.25, "en": 0.3, "es": 0.3, "et": 0.15, "eu": 0.183333, "fa": 0.333333, "fi": 0.275, "fr": 0.25, "gl": 0.166667, "hu": 0.275, "hv": 0.275, "is": 0.375, "it": 0.275, "ka": 0.2, "la": 0.4, "li": 0.205128, "lv": 0.325, "mk": 0.2, "mt": 0.1, "nl": 0.225, "no": 0.25, "pl": 0.3, "pt": 0.25, "ro": 0.222222, "ru": 0.3, "sk": 0.142857, "sl": 0.193548, "sq": 0.157895, "sr": 0.2, "stack": 0.233333, "sv": 0.3, "tr": 0.175, "uk": 0.225}, "lang_wp": {"ar": 0.4125, "az": 0.4375, "be": 0.4875, "bg": 0.425, "bo": 0.45, "ca": 0.425, "cn": 0.55, "cs": 0.3875, "da": 0.55, "de": 0.5, "el": 0.3625, "en": 0.4125, "es": 0.425, "et": 0.4, "eu": 0.458333, "fa": 0.575, "fi": 0.3875, "fr": 0.425, "gl": 0.408333, "hu": 0.4875, "hv": 0.5125, "is": 0.6, "it": 0.4125, "ka": 0.375, "la": 0.566667, "li": 0.423077, "lv": 0.575, "mk": 0.3625, "mt": 0.35, "nl": 0.4125, "no": 0.375, "pl": 0.483333, "pt": 0.4, "ro": 0.375, "ru": 0.416667, "sk": 0.410714, "sl": 0.467742, "sq": 0.513158, "sr": 0.4625, "stack": 0.466667, "sv": 0.4375, "tr": 0.5125, "uk": 0.3875}}, {"model": "mistralai/mistral-7b-instruct", "avg_exact": 0.24472, "avg_wp": 0.419565, "total": 1610, "lang_exact": {"ar": 0.058824, "az": 0.27027, "be": 0.382353, "bg": 0.243243, "bo": 0.314286, "ca": 0.285714, "cn": 0.339286, "cs": 0.428571, "da": 0.28, "de": 0.25, "el": 0.194444, "en": 0.125, "es": 0.241379, "et": 0.482759, "eu": 0.226415, "fa": 0.355932, "fi": 0.269231, "fr": 0.184211, "gl": 0.206897, "hu": 0.138889, "hv": 0.361111, "is": 0.166667, "it": 0.28125, "ka": 0.277778, "la": 0.241379, "li": 0.171429, "lv": 0.142857, "mk": 0.205128, "mt": 0.162162, "nl": 0.285714, "no": 0.205128, "pl": 0.272727, "pt": 0.189189, "ro": 0.138889, "ru": 0.354839, "sk": 0.236842, "sl": 0.289474, "sq": 0.27027, "sr": 0.282051, "stack": 0.269231, "sv": 0.210526, "tr": 0.102564, "uk": 0.175}, "lang_wp": {"ar": 0.191176, "az": 0.445946, "be": 0.558824, "bg": 0.432432, "bo": 0.542857, "ca": 0.457143, "cn": 0.508929, "cs": 0.52381, "da": 0.4, "de": 0.3125, "el": 0.388889, "en": 0.265625, "es": 0.396552, "et": 0.62069, "eu": 0.349057, "fa": 0.542373, "fi": 0.365385, "fr": 0.381579, "gl": 0.387931, "hu": 0.319444, "hv": 0.513889, "is": 0.416667, "it": 0.5, "ka": 0.416667, "la": 0.431034, "li": 0.285714, "lv": 0.328571, "mk": 0.397436, "mt": 0.337838, "nl": 0.5, "no": 0.384615, "pl": 0.445455, "pt": 0.378378, "ro": 0.333333, "ru": 0.467742, "sk": 0.434211, "sl": 0.394737, "sq": 0.486486, "sr": 0.487179, "stack": 0.480769, "sv": 0.421053, "tr": 0.320513, "uk": 0.35}}, {"model": "mistralai/mistral-small-24b-instruct-2501", "avg_exact": 0.185691, "avg_wp": 0.368378, "total": 1831, "lang_exact": {"ar": 0.05, "az": 0.25, "be": 0.075, "bg": 0.2, "bo": 0.25, "ca": 0.25, "cn": 0.254237, "cs": 0.15, "da": 0.225, "de": 0.5, "el": 0.2, "en": 0.25, "es": 0.25, "et": 0.25, "eu": 0.2, "fa": 0.2, "fi": 0.225, "fr": 0.225, "gl": 0.183333, "hu": 0.125, "hv": 0.175, "is": 0.15, "it": 0.25, "ka": 0.025, "la": 0.35, "li": 0.05, "lv": 0.125, "mk": 0.225, "mt": 0.25, "nl": 0.175, "no": 0.225, "pl": 0.233333, "pt": 0.225, "ro": 0.1, "ru": 0.0, "sk": 0.15, "sl": 0.225, "sq": 0.025, "sr": 0.0, "stack": 0.25, "sv": 0.25, "tr": 0.075, "uk": 0.075}, "lang_wp": {"ar": 0.225, "az": 0.45, "be": 0.3125, "bg": 0.4375, "bo": 0.3875, "ca": 0.3625, "cn": 0.457627, "cs": 0.3375, "da": 0.375, "de": 0.5, "el": 0.35, "en": 0.4125, "es": 0.4125, "et": 0.4125, "eu": 0.358333, "fa": 0.4, "fi": 0.3375, "fr": 0.375, "gl": 0.291667, "hu": 0.275, "hv": 0.35, "is": 0.375, "it": 0.4, "ka": 0.2625, "la": 0.516667, "li": 0.3, "lv": 0.3625, "mk": 0.375, "mt": 0.4, "nl": 0.3375, "no": 0.3625, "pl": 0.416667, "pt": 0.4125, "ro": 0.225, "ru": 0.28125, "sk": 0.325, "sl": 0.475, "sq": 0.375, "sr": 0.225, "stack": 0.475, "sv": 0.4, "tr": 0.275, "uk": 0.325}}, {"model": "mistralai/ministral-14b-2512", "avg_exact": 0.196945, "avg_wp": 0.355701, "total": 1833, "lang_exact": {"ar": 0.15, "az": 0.225, "be": 0.175, "bg": 0.2, "bo": 0.25, "ca": 0.225, "cn": 0.233333, "cs": 0.25, "da": 0.175, "de": 0.25, "el": 0.25, "en": 0.275, "es": 0.175, "et": 0.075, "eu": 0.266667, "fa": 0.216667, "fi": 0.125, "fr": 0.25, "gl": 0.216667, "hu": 0.175, "hv": 0.2, "is": 0.325, "it": 0.125, "ka": 0.05, "la": 0.416667, "li": 0.125, "lv": 0.1, "mk": 0.175, "mt": 0.05, "nl": 0.1, "no": 0.125, "pl": 0.233333, "pt": 0.15, "ro": 0.175, "ru": 0.181818, "sk": 0.175, "sl": 0.125, "sq": 0.175, "sr": 0.225, "stack": 0.2, "sv": 0.275, "tr": 0.225, "uk": 0.2}, "lang_wp": {"ar": 0.3125, "az": 0.3625, "be": 0.35, "bg": 0.4125, "bo": 0.35, "ca": 0.4, "cn": 0.425, "cs": 0.4125, "da": 0.325, "de": 0.35, "el": 0.375, "en": 0.4125, "es": 0.35, "et": 0.225, "eu": 0.425, "fa": 0.441667, "fi": 0.275, "fr": 0.375, "gl": 0.383333, "hu": 0.3, "hv": 0.3375, "is": 0.4875, "it": 0.3125, "ka": 0.2125, "la": 0.533333, "li": 0.2625, "lv": 0.2875, "mk": 0.3375, "mt": 0.175, "nl": 0.225, "no": 0.225, "pl": 0.433333, "pt": 0.2875, "ro": 0.3375, "ru": 0.333333, "sk": 0.3375, "sl": 0.325, "sq": 0.3375, "sr": 0.325, "stack": 0.425, "sv": 0.4, "tr": 0.425, "uk": 0.375}}, {"model": "meta-llama/llama-3.1-8b-instruct", "avg_exact": 0.211044, "avg_wp": 0.344997, "total": 1829, "lang_exact": {"ar": 0.135135, "az": 0.2, "be": 0.3, "bg": 0.175, "bo": 0.2, "ca": 0.225, "cn": 0.3, "cs": 0.25, "da": 0.25, "de": 0.35, "el": 0.225, "en": 0.275, "es": 0.075, "et": 0.275, "eu": 0.116667, "fa": 0.083333, "fi": 0.333333, "fr": 0.1, "gl": 0.133333, "hu": 0.175, "hv": 0.375, "is": 0.25, "it": 0.2, "ka": 0.225, "la": 0.116667, "li": 0.2, "lv": 0.225, "mk": 0.275, "mt": 0.2, "nl": 0.225, "no": 0.225, "pl": 0.083333, "pt": 0.225, "ro": 0.075, "ru": 0.242424, "sk": 0.225, "sl": 0.25, "sq": 0.225, "sr": 0.25, "stack": 0.216667, "sv": 0.375, "tr": 0.275, "uk": 0.225}, "lang_wp": {"ar": 0.297297, "az": 0.275, "be": 0.4625, "bg": 0.3375, "bo": 0.3125, "ca": 0.35, "cn": 0.441667, "cs": 0.4, "da": 0.3875, "de": 0.375, "el": 0.325, "en": 0.4, "es": 0.2125, "et": 0.3875, "eu": 0.191667, "fa": 0.216667, "fi": 0.5, "fr": 0.2375, "gl": 0.266667, "hu": 0.3375, "hv": 0.5375, "is": 0.375, "it": 0.325, "ka": 0.35, "la": 0.325, "li": 0.3, "lv": 0.4, "mk": 0.4, "mt": 0.3, "nl": 0.3625, "no": 0.3375, "pl": 0.258333, "pt": 0.35, "ro": 0.2, "ru": 0.30303, "sk": 0.3625, "sl": 0.375, "sq": 0.3375, "sr": 0.375, "stack": 0.45, "sv": 0.475, "tr": 0.4, "uk": 0.3625}}, {"model": "speakleash/Bielik-11B-v2.6-Instruct", "avg_exact": 0.152459, "avg_wp": 0.343989, "total": 1830, "lang_exact": {"ar": 0.05, "az": 0.075, "be": 0.0, "bg": 0.175, "bo": 0.2, "ca": 0.175, "cn": 0.186441, "cs": 0.1, "da": 0.225, "de": 0.0, "el": 0.275, "en": 0.025, "es": 0.2, "et": 0.2, "eu": 0.166667, "fa": 0.266667, "fi": 0.125, "fr": 0.225, "gl": 0.216667, "hu": 0.2, "hv": 0.225, "is": 0.0, "it": 0.125, "ka": 0.0, "la": 0.2, "li": 0.225, "lv": 0.125, "mk": 0.2, "mt": 0.15, "nl": 0.225, "no": 0.15, "pl": 0.183333, "pt": 0.075, "ro": 0.075, "ru": 0.090909, "sk": 0.125, "sl": 0.225, "sq": 0.0, "sr": 0.05, "stack": 0.266667, "sv": 0.15, "tr": 0.225, "uk": 0.076923}, "lang_wp": {"ar": 0.175, "az": 0.25, "be": 0.1875, "bg": 0.3875, "bo": 0.4, "ca": 0.425, "cn": 0.29661, "cs": 0.3, "da": 0.4125, "de": 0.25, "el": 0.45, "en": 0.2, "es": 0.4625, "et": 0.4375, "eu": 0.333333, "fa": 0.433333, "fi": 0.35, "fr": 0.4375, "gl": 0.333333, "hu": 0.3375, "hv": 0.4375, "is": 0.1125, "it": 0.375, "ka": 0.128205, "la": 0.308333, "li": 0.4375, "lv": 0.3875, "mk": 0.4125, "mt": 0.35, "nl": 0.4625, "no": 0.4125, "pl": 0.4, "pt": 0.4125, "ro": 0.2625, "ru": 0.30303, "sk": 0.2875, "sl": 0.4375, "sq": 0.2, "sr": 0.2, "stack": 0.483333, "sv": 0.3375, "tr": 0.375, "uk": 0.25641}}, {"model": "CYFRAGOVPL/Llama-PLLuM-70B-chat-250801", "avg_exact": 0.232533, "avg_wp": 0.342522, "total": 1832, "lang_exact": {"ar": 0.15, "az": 0.275, "be": 0.25, "bg": 0.175, "bo": 0.25, "ca": 0.175, "cn": 0.152542, "cs": 0.225, "da": 0.175, "de": 0.5, "el": 0.225, "en": 0.225, "es": 0.125, "et": 0.25, "eu": 0.1, "fa": 0.35, "fi": 0.25, "fr": 0.225, "gl": 0.133333, "hu": 0.175, "hv": 0.375, "is": 0.4, "it": 0.2, "ka": 0.175, "la": 0.3, "li": 0.25, "lv": 0.325, "mk": 0.225, "mt": 0.275, "nl": 0.25, "no": 0.25, "pl": 0.1, "pt": 0.25, "ro": 0.25, "ru": 0.30303, "sk": 0.2, "sl": 0.175, "sq": 0.25, "sr": 0.325, "stack": 0.3, "sv": 0.25, "tr": 0.275, "uk": 0.15}, "lang_wp": {"ar": 0.35, "az": 0.4, "be": 0.3625, "bg": 0.275, "bo": 0.4, "ca": 0.2375, "cn": 0.194915, "cs": 0.375, "da": 0.2875, "de": 0.525, "el": 0.3125, "en": 0.2375, "es": 0.125, "et": 0.375, "eu": 0.183333, "fa": 0.508333, "fi": 0.3625, "fr": 0.35, "gl": 0.2, "hu": 0.2125, "hv": 0.55, "is": 0.5875, "it": 0.275, "ka": 0.2375, "la": 0.5, "li": 0.35, "lv": 0.4625, "mk": 0.275, "mt": 0.4625, "nl": 0.3625, "no": 0.3125, "pl": 0.141667, "pt": 0.3625, "ro": 0.3625, "ru": 0.439394, "sk": 0.325, "sl": 0.2875, "sq": 0.375, "sr": 0.475, "stack": 0.483333, "sv": 0.375, "tr": 0.4125, "uk": 0.2375}}, {"model": "CYFRAGOVPL/pllum-12b-nc-chat-250715", "avg_exact": 0.144651, "avg_wp": 0.232533, "total": 1832, "lang_exact": {"ar": 0.075, "az": 0.175, "be": 0.275, "bg": 0.125, "bo": 0.325, "ca": 0.275, "cn": 0.101695, "cs": 0.075, "da": 0.125, "de": 0.15, "el": 0.175, "en": 0.15, "es": 0.2, "et": 0.075, "eu": 0.083333, "fa": 0.216667, "fi": 0.075, "fr": 0.25, "gl": 0.1, "hu": 0.025, "hv": 0.325, "is": 0.15, "it": 0.125, "ka": 0.075, "la": 0.133333, "li": 0.15, "lv": 0.1, "mk": 0.075, "mt": 0.1, "nl": 0.075, "no": 0.2, "pl": 0.116667, "pt": 0.1, "ro": 0.35, "ru": 0.212121, "sk": 0.15, "sl": 0.15, "sq": 0.075, "sr": 0.175, "stack": 0.083333, "sv": 0.125, "tr": 0.15, "uk": 0.075}, "lang_wp": {"ar": 0.0875, "az": 0.3375, "be": 0.3625, "bg": 0.2, "bo": 0.4875, "ca": 0.3625, "cn": 0.144068, "cs": 0.1125, "da": 0.2125, "de": 0.25, "el": 0.25, "en": 0.275, "es": 0.275, "et": 0.15, "eu": 0.116667, "fa": 0.35, "fi": 0.1375, "fr": 0.3875, "gl": 0.183333, "hu": 0.125, "hv": 0.475, "is": 0.225, "it": 0.225, "ka": 0.1125, "la": 0.308333, "li": 0.2125, "lv": 0.2375, "mk": 0.15, "mt": 0.2, "nl": 0.15, "no": 0.275, "pl": 0.141667, "pt": 0.1375, "ro": 0.425, "ru": 0.30303, "sk": 0.2625, "sl": 0.3, "sq": 0.1375, "sr": 0.25, "stack": 0.183333, "sv": 0.1625, "tr": 0.2625, "uk": 0.175}}];
|
| 132 |
+
const ALL_LANGS = ["ar", "az", "be", "bg", "bo", "ca", "cn", "cs", "da", "de", "el", "en", "es", "et", "eu", "fa", "fi", "fr", "gl", "hu", "hv", "is", "it", "ka", "la", "li", "lv", "mk", "mt", "nl", "no", "pl", "pt", "ro", "ru", "sk", "sl", "sq", "sr", "stack", "sv", "tr", "uk"];
|
| 133 |
+
const LANG_NAMES = {"af": "Afrikaans", "ar": "Arabic", "az": "Azerbaijani", "be": "Belarusian", "bg": "Bulgarian", "bn": "Bengali", "ca": "Catalan", "cs": "Czech", "cy": "Welsh", "da": "Danish", "de": "German", "el": "Greek", "en": "English", "eo": "Esperanto", "es": "Spanish", "et": "Estonian", "eu": "Basque", "fa": "Persian", "fi": "Finnish", "fr": "French", "ga": "Irish", "gl": "Galician", "gu": "Gujarati", "he": "Hebrew", "hi": "Hindi", "hr": "Croatian", "hu": "Hungarian", "hy": "Armenian", "id": "Indonesian", "is": "Icelandic", "it": "Italian", "ja": "Japanese", "ka": "Georgian", "kk": "Kazakh", "km": "Khmer", "kn": "Kannada", "ko": "Korean", "lt": "Lithuanian", "lv": "Latvian", "mk": "Macedonian", "ml": "Malayalam", "mn": "Mongolian", "mr": "Marathi", "ms": "Malay", "mt": "Maltese", "my": "Burmese", "ne": "Nepali", "nl": "Dutch", "no": "Norwegian", "pa": "Punjabi", "pl": "Polish", "pt": "Portuguese", "ro": "Romanian", "ru": "Russian", "si": "Sinhala", "sk": "Slovak", "sl": "Slovenian", "sq": "Albanian", "sr": "Serbian", "sv": "Swedish", "sw": "Swahili", "ta": "Tamil", "te": "Telugu", "th": "Thai", "tl": "Filipino", "tr": "Turkish", "uk": "Ukrainian", "ur": "Urdu", "uz": "Uzbek", "vi": "Vietnamese", "zh": "Chinese", "zu": "Zulu"};
|
| 134 |
|
| 135 |
+
function langName(c) { return LANG_NAMES[c] || c.toUpperCase(); }
|
| 136 |
|
| 137 |
+
function scoreColor(v) {
|
| 138 |
+
const r = v < 0.5 ? 220 : Math.round(220 - (v - 0.5) * 2 * 160);
|
| 139 |
+
const g = v > 0.5 ? 160 : Math.round(v * 2 * 160);
|
| 140 |
+
return `rgb(${r},${g},40)`;
|
| 141 |
+
}
|
| 142 |
+
function textColor(v) { return v > 0.35 ? '#fff' : '#ccc'; }
|
| 143 |
+
|
| 144 |
+
let selLangs = [];
|
| 145 |
+
let sortCol = 'avg';
|
| 146 |
+
let sortDir = -1;
|
| 147 |
+
let metric = 'wp';
|
| 148 |
+
|
| 149 |
+
window.setMetric = function(m) {
|
| 150 |
+
metric = m;
|
| 151 |
+
document.getElementById('btn-wp').classList.toggle('active', m === 'wp');
|
| 152 |
+
document.getElementById('btn-ex').classList.toggle('active', m === 'ex');
|
| 153 |
+
render();
|
| 154 |
+
};
|
| 155 |
+
|
| 156 |
+
function getScore(row, lang) {
|
| 157 |
+
if (lang) return metric === 'wp' ? row.lang_wp[lang] : row.lang_exact[lang];
|
| 158 |
+
return metric === 'wp' ? row.avg_wp : row.avg_exact;
|
| 159 |
+
}
|
| 160 |
+
|
| 161 |
+
// chips
|
| 162 |
+
const chipsEl = document.getElementById('chips');
|
| 163 |
+
function renderChips() {
|
| 164 |
+
chipsEl.innerHTML = '';
|
| 165 |
+
function mk(label, key, active) {
|
| 166 |
+
const s = document.createElement('span');
|
| 167 |
+
s.className = 'chip' + (active ? ' active' : '');
|
| 168 |
+
s.textContent = label;
|
| 169 |
+
s.onclick = () => {
|
| 170 |
+
if (key === '__all__') { selLangs = []; }
|
| 171 |
+
else {
|
| 172 |
+
const i = selLangs.indexOf(key);
|
| 173 |
+
i >= 0 ? selLangs.splice(i, 1) : selLangs.push(key);
|
| 174 |
+
}
|
| 175 |
+
render();
|
| 176 |
};
|
| 177 |
+
chipsEl.appendChild(s);
|
|
|
|
| 178 |
}
|
| 179 |
+
mk('All', '__all__', selLangs.length === 0);
|
| 180 |
+
ALL_LANGS.forEach(l => mk(langName(l), l, selLangs.includes(l)));
|
| 181 |
+
}
|
| 182 |
+
|
| 183 |
+
// chart
|
| 184 |
+
let chartInstance = null;
|
| 185 |
+
function renderChart() {
|
| 186 |
+
const sorted = [...ALL_ROWS].sort((a, b) => b.avg_wp - a.avg_wp);
|
| 187 |
+
const labels = sorted.map(r => r.model);
|
| 188 |
+
const wpData = sorted.map(r => +(r.avg_wp * 100).toFixed(1));
|
| 189 |
+
const exData = sorted.map(r => +(r.avg_exact * 100).toFixed(1));
|
| 190 |
+
|
| 191 |
+
const ctx = document.getElementById('globalChart').getContext('2d');
|
| 192 |
+
if (chartInstance) chartInstance.destroy();
|
| 193 |
|
| 194 |
+
const h = Math.max(320, sorted.length * 32 + 80);
|
| 195 |
+
document.getElementById('globalChart').style.height = h + 'px';
|
| 196 |
+
|
| 197 |
+
chartInstance = new Chart(ctx, {
|
| 198 |
+
type: 'bar',
|
| 199 |
+
data: {
|
| 200 |
+
labels,
|
| 201 |
+
datasets: [
|
| 202 |
+
{
|
| 203 |
+
label: 'Weighted Score',
|
| 204 |
+
data: wpData,
|
| 205 |
+
backgroundColor: '#2563eb',
|
| 206 |
+
borderRadius: 3,
|
| 207 |
+
barPercentage: 0.72,
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
label: 'Exact Accuracy',
|
| 211 |
+
data: exData,
|
| 212 |
+
backgroundColor: '#16a34a',
|
| 213 |
+
borderRadius: 3,
|
| 214 |
+
barPercentage: 0.72,
|
| 215 |
+
},
|
| 216 |
+
]
|
| 217 |
+
},
|
| 218 |
+
options: {
|
| 219 |
+
indexAxis: 'y',
|
| 220 |
+
responsive: true,
|
| 221 |
+
maintainAspectRatio: false,
|
| 222 |
+
animation: { duration: 500 },
|
| 223 |
+
plugins: {
|
| 224 |
+
legend: {
|
| 225 |
+
position: 'bottom',
|
| 226 |
+
labels: {
|
| 227 |
+
color: '#94a3b8',
|
| 228 |
+
font: { family: 'JetBrains Mono', size: 11 },
|
| 229 |
+
boxWidth: 14, padding: 20,
|
| 230 |
+
}
|
| 231 |
+
},
|
| 232 |
+
tooltip: {
|
| 233 |
+
backgroundColor: '#1e2a3a',
|
| 234 |
+
titleColor: '#e2e8f0',
|
| 235 |
+
bodyColor: '#94a3b8',
|
| 236 |
+
callbacks: {
|
| 237 |
+
label: ctx => ` ${ctx.dataset.label}: ${ctx.parsed.x}%`
|
| 238 |
+
}
|
| 239 |
+
},
|
| 240 |
+
},
|
| 241 |
+
scales: {
|
| 242 |
+
x: {
|
| 243 |
+
min: 0, max: 108,
|
| 244 |
+
grid: { color: '#1a2236' },
|
| 245 |
+
ticks: {
|
| 246 |
+
color: '#64748b',
|
| 247 |
+
font: { family: 'JetBrains Mono', size: 10 },
|
| 248 |
+
callback: v => v + '%',
|
| 249 |
+
},
|
| 250 |
+
title: {
|
| 251 |
+
display: true, text: 'Percent (%)',
|
| 252 |
+
color: '#64748b',
|
| 253 |
+
font: { family: 'JetBrains Mono', size: 11 },
|
| 254 |
+
}
|
| 255 |
+
},
|
| 256 |
+
y: {
|
| 257 |
+
grid: { display: false },
|
| 258 |
+
ticks: {
|
| 259 |
+
color: '#cbd5e1',
|
| 260 |
+
font: { family: 'JetBrains Mono', size: 11 },
|
| 261 |
+
}
|
| 262 |
+
}
|
| 263 |
+
}
|
| 264 |
+
}
|
| 265 |
+
});
|
| 266 |
+
}
|
| 267 |
+
|
| 268 |
+
// table
|
| 269 |
+
function render() {
|
| 270 |
+
renderChips();
|
| 271 |
+
|
| 272 |
+
const visLangs = selLangs.length > 0 ? [...selLangs].sort() : [...ALL_LANGS];
|
| 273 |
+
|
| 274 |
+
let rows = ALL_ROWS.map(row => {
|
| 275 |
+
const ls = {};
|
| 276 |
+
visLangs.forEach(l => { const v = getScore(row, l); if (v !== undefined) ls[l] = v; });
|
| 277 |
+
const vals = Object.values(ls);
|
| 278 |
+
const avg = selLangs.length === 0
|
| 279 |
+
? getScore(row, null)
|
| 280 |
+
: (vals.length ? vals.reduce((a, b) => a + b, 0) / vals.length : null);
|
| 281 |
+
return { ...row, _avg: avg, _ls: ls };
|
| 282 |
+
}).filter(r => r._avg !== null);
|
| 283 |
+
|
| 284 |
+
rows.sort((a, b) => {
|
| 285 |
+
const va = sortCol === 'avg' ? a._avg : (a._ls[sortCol] ?? -1);
|
| 286 |
+
const vb = sortCol === 'avg' ? b._avg : (b._ls[sortCol] ?? -1);
|
| 287 |
+
return sortDir * (vb - va);
|
| 288 |
+
});
|
| 289 |
+
|
| 290 |
+
// header
|
| 291 |
+
const head = document.getElementById('lb-head');
|
| 292 |
+
const mkBtn = (label, col) => {
|
| 293 |
+
const active = sortCol === col;
|
| 294 |
+
const arrow = active ? (sortDir === -1 ? ' β' : ' β') : '';
|
| 295 |
+
return `<button class="sort-btn${active ? ' active' : ''}" data-col="${col}">${label}${arrow}</button>`;
|
| 296 |
+
};
|
| 297 |
+
const ml = metric === 'wp' ? 'Wtd Score' : 'Exact Acc';
|
| 298 |
+
head.innerHTML = `<tr>
|
| 299 |
+
<th class="rank-col"></th>
|
| 300 |
+
<th class="model-col"><span style="font-size:10px;text-transform:uppercase;letter-spacing:.08em;color:#475569">Model</span></th>
|
| 301 |
+
<th class="avg-col">${mkBtn(ml + ' avg', 'avg')}</th>
|
| 302 |
+
${visLangs.map(l => `<th class="lang-col">${mkBtn(langName(l), l)}</th>`).join('')}
|
| 303 |
+
</tr>`;
|
| 304 |
+
head.querySelectorAll('.sort-btn').forEach(btn => {
|
| 305 |
+
btn.onclick = () => {
|
| 306 |
+
const col = btn.dataset.col;
|
| 307 |
+
sortCol === col ? (sortDir = -sortDir) : (sortCol = col, sortDir = -1);
|
| 308 |
+
render();
|
| 309 |
};
|
| 310 |
+
});
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 311 |
|
| 312 |
+
// body
|
| 313 |
+
const body = document.getElementById('lb-body');
|
| 314 |
+
body.innerHTML = rows.map((row, i) => {
|
| 315 |
+
const avgPct = (row._avg * 100).toFixed(1) + '%';
|
| 316 |
+
const langCells = visLangs.map(l => {
|
| 317 |
+
const v = row._ls[l];
|
| 318 |
+
if (v === undefined) return `<td class="empty">β</td>`;
|
| 319 |
+
return `<td class="score" style="background:${scoreColor(v)};color:${textColor(v)}">${(v * 100).toFixed(1)}%</td>`;
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 320 |
}).join('');
|
| 321 |
+
return `<tr>
|
| 322 |
+
<td class="rank">${i + 1}</td>
|
| 323 |
+
<td class="model" title="${row.model}">${row.model}</td>
|
| 324 |
+
<td class="score" style="background:${scoreColor(row._avg)};color:${textColor(row._avg)};font-size:13px;font-weight:800">${avgPct}</td>
|
| 325 |
+
${langCells}
|
| 326 |
+
</tr>`;
|
| 327 |
+
}).join('');
|
| 328 |
|
| 329 |
+
document.getElementById('footer').textContent =
|
| 330 |
+
`63371 predictions Β· ${ALL_LANGS.length} languages Β· ${ALL_ROWS.length} models`;
|
| 331 |
+
}
|
|
|
|
| 332 |
|
| 333 |
+
render();
|
| 334 |
+
renderChart();
|
| 335 |
+
})();
|
| 336 |
+
</script>
|
| 337 |
</body>
|
| 338 |
+
</html>
|