Update benchmark leaderboard
Browse files- index.html +5 -5
index.html
CHANGED
|
@@ -284,7 +284,7 @@
|
|
| 284 |
|
| 285 |
<script>
|
| 286 |
(function() {
|
| 287 |
-
const ALL_ROWS = [{"model": "meta-llama/Llama-3.3-70B-Instruct", "avg_exact": 0.
|
| 288 |
const ALL_LANGS = ["sq", "ab", "ar", "az", "eu", "be", "bo", "bg", "ca", "cn", "hv", "cs", "da", "nl", "en", "et", "fa", "fi", "fr", "gl", "ka", "de", "el", "he", "hi", "hu", "is", "ir", "it", "kz", "la", "lv", "li", "mk", "mt", "no", "pl", "pt", "ro", "ru", "sr", "sk", "sl", "es", "sv", "tr", "uk", "cy"];
|
| 289 |
const LANG_NAMES = {"af": "Afrikaans", "ab": "Arabic", "az": "Azerbaijani", "ar": "Armenian", "be": "Belarusian", "bo": "Bosnian", "bg": "Bulgarian", "bn": "Brunei", "ca": "Catalan", "cs": "Czech", "cn": "Chinese", "cy": "Welsh", "da": "Danish", "de": "German", "el": "Greek", "en": "English", "eo": "Esperanto", "es": "Spanish", "et": "Estonian", "eu": "Basque", "fa": "Faroese", "fi": "Finnish", "fr": "French", "ga": "Irish", "gl": "Galician", "gu": "Gujarati", "he": "Hebrew", "hi": "Hindi", "hr": "Croatian", "hu": "Hungarian", "hv": "Croatia", "id": "Indonesian", "is": "Icelandic", "it": "Italian", "ir": "Irish", "ja": "Japanese", "ka": "Georgian", "kz": "Kazakh", "km": "Khmer", "kn": "Kannada", "ko": "Korean", "la": "Latin", "li": "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", "pe": "Persian", "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"};
|
| 290 |
const LANG_COUNTS = {"ab": 600, "ar": 400, "az": 400, "be": 400, "bg": 362, "bo": 400, "ca": 359, "cn": 600, "cs": 400, "cy": 600, "da": 400, "de": 600, "el": 400, "en": 600, "es": 333, "et": 400, "eu": 597, "fa": 600, "fi": 400, "fr": 382, "gl": 600, "he": 600, "hi": 544, "hu": 400, "hv": 400, "ir": 600, "is": 400, "it": 400, "ka": 318, "kz": 600, "la": 513, "li": 400, "lv": 400, "mk": 400, "mt": 400, "nl": 400, "no": 400, "pl": 571, "pt": 400, "ro": 400, "ru": 600, "sk": 400, "sl": 400, "sq": 400, "sr": 400, "sv": 400, "tr": 400, "uk": 574};
|
|
@@ -292,11 +292,11 @@
|
|
| 292 |
|
| 293 |
// second dataset
|
| 294 |
const HAS_SECOND = true;
|
| 295 |
-
const ALL_ROWS_2 = [{"model": "allenai/Olmo-3.1-32B-Instruct", "avg_exact": 0.312393, "avg_wp": 0.507738, "avg_bias": 0.4911, "avg_parsed": 0.999475, "avg_mae": 1.1207, "total": 7625, "lang_exact": {"ab": 0.295812, "cn": 0.377358, "cy": 0.277551, "de": 0.314286, "en": 0.39083, "es": 0.314815, "eu": 0.281843, "fr": 0.356364, "gl": 0.309859, "he": 0.227273, "hi": 0.249493, "ir": 0.271255, "kz": 0.189573, "la": 0.435714, "pl": 0.377737, "sl": 0.345098, "uk": 0.273608}, "lang_wp": {"ab": 0.485602, "cn": 0.600943, "cy": 0.50102, "de": 0.516071, "en": 0.601528, "es": 0.528704, "eu": 0.501355, "fr": 0.544545, "gl": 0.482897, "he": 0.422727, "hi": 0.447262, "ir": 0.446356, "kz": 0.386256, "la": 0.457143, "pl": 0.555657, "sl": 0.521569, "uk": 0.495157}, "lang_parsed": {"ab": 0.997382, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 0.998182, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 0.996078, "uk": 1.0}, "lang_mae": {"ab": 1.252, "cn": 0.8623, "cy": 1.102, "de": 1.0893, "en": 0.8908, "es": 0.9907, "eu": 1.1274, "fr": 1.0055, "gl": 1.169, "he": 1.3409, "hi": 1.2373, "ir": 1.2449, "kz": 1.4787, "la": 1.9714, "pl": 1.0018, "sl": 1.1043, "uk": 1.0944}, "confusion": {"1": {"1": 0.3559, "3": 0.3783, "6": 0.0437, "2": 0.0353, "4": 0.1608, "5": 0.026}, "2": {"1": 0.1208, "3": 0.426, "4": 0.2703, "5": 0.0691, "6": 0.0887, "2": 0.0251}, "3": {"3": 0.3674, "2": 0.011, "4": 0.3909, "5": 0.1242, "6": 0.0742, "1": 0.0323}, "4": {"3": 0.2456, "4": 0.3828, "6": 0.1464, "5": 0.1992, "1": 0.026}, "5": {"6": 0.289, "5": 0.34, "4": 0.2492, "3": 0.1083, "1": 0.0119, "2": 0.0016}, "6": {"5": 0.2819, "6": 0.4577, "4": 0.1805, "3": 0.0502, "1": 0.0288, "2": 0.0009}}}, {"model": "utter-project/EuroLLM-22B-Instruct-2512", "avg_exact": 0.269039, "avg_wp": 0.451716, "avg_bias": -0.0838, "avg_parsed": 0.989284, "avg_mae": 1.3787, "total": 7839, "lang_exact": {"ab": 0.204651, "cn": 0.341328, "cy": 0.216942, "de": 0.319298, "en": 0.299539, "es": 0.301294, "eu": 0.203804, "fr": 0.317029, "gl": 0.192233, "he": 0.26097, "hi": 0.269373, "ir": 0.275728, "kz": 0.271186, "la": 0.172662, "pl": 0.254902, "sl": 0.319231, "uk": 0.238512}, "lang_wp": {"ab": 0.305814, "cn": 0.550738, "cy": 0.391529, "de": 0.528947, "en": 0.498848, "es": 0.474122, "eu": 0.418478, "fr": 0.500906, "gl": 0.375728, "he": 0.413395, "hi": 0.429889, "ir": 0.463107, "kz": 0.491525, "la": 0.503597, "pl": 0.382353, "sl": 0.515385, "uk": 0.446389}, "lang_parsed": {"ab": 0.997674, "cn": 0.994465, "cy": 0.977273, "de": 1.0, "en": 1.0, "es": 0.998152, "eu": 1.0, "fr": 0.990942, "gl": 0.941748, "he": 0.923788, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 2.2168, "cn": 0.9666, "cy": 1.4947, "de": 1.0912, "en": 1.1636, "es": 1.3056, "eu": 1.4375, "fr": 1.1499, "gl": 1.5588, "he": 1.4125, "hi": 1.6144, "ir": 1.3107, "kz": 1.2034, "la": 1.2734, "pl": 1.8164, "sl": 1.1077, "uk": 1.3042}, "confusion": {"2": {"1": 0.4793, "3": 0.0716, "5": 0.3635, "4": 0.0554, "2": 0.0302}, "1": {"1": 0.7788, "2": 0.0221, "3": 0.0498, "5": 0.1143, "4": 0.0332, "6": 0.0018}, "4": {"1": 0.2238, "5": 0.6674, "6": 0.0007, "3": 0.0474, "4": 0.0544, "2": 0.0063}, "3": {"1": 0.3294, "5": 0.5033, "4": 0.0778, "3": 0.0734, "2": 0.0117, "6": 0.0044}, "5": {"1": 0.1667, "5": 0.7823, "6": 0.0046, "4": 0.0282, "3": 0.0175, "2": 0.0008}, "6": {"1": 0.1984, "5": 0.7628, "4": 0.0141, "6": 0.0132, "3": 0.0097, "2": 0.0018}}}, {"model": "cjvt/GaMS3-12B-Instruct", "avg_exact": 0.235073, "avg_wp": 0.386782, "avg_bias": -0.3635, "avg_parsed": 0.886469, "avg_mae": 1.4487, "total": 7989, "lang_exact": {"ab": 0.207675, "cn": 0.25859, "cy": 0.162602, "de": 0.273205, "en": 0.296703, "es": 0.289134, "eu": 0.120321, "fr": 0.304505, "gl": 0.061896, "he": 0.242545, "hi": 0.287796, "ir": 0.163022, "kz": 0.128405, "la": 0.524138, "pl": 0.28777, "sl": 0.228682, "uk": 0.262582}, "lang_wp": {"ab": 0.308126, "cn": 0.43038, "cy": 0.305894, "de": 0.443082, "en": 0.483516, "es": 0.480663, "eu": 0.255348, "fr": 0.461261, "gl": 0.147969, "he": 0.378728, "hi": 0.439891, "ir": 0.332008, "kz": 0.321012, "la": 0.572414, "pl": 0.436151, "sl": 0.361434, "uk": 0.458425}, "lang_parsed": {"ab": 0.875847, "cn": 0.962025, "cy": 0.857724, "de": 0.894921, "en": 0.951648, "es": 1.0, "eu": 0.703209, "fr": 0.927928, "gl": 0.613153, "he": 0.914513, "hi": 0.87796, "ir": 0.998012, "kz": 0.891051, "la": 1.0, "pl": 0.895683, "sl": 0.839147, "uk": 0.894967}, "lang_mae": {"ab": 1.9691, "cn": 1.3759, "cy": 1.6872, "de": 1.182, "en": 1.2055, "es": 1.2615, "eu": 1.4791, "fr": 1.3398, "gl": 2.4132, "he": 1.5739, "hi": 1.2531, "ir": 1.6494, "kz": 1.5153, "la": 1.2966, "pl": 1.3233, "sl": 1.3741, "uk": 1.1051}, "confusion": {"1": {"1": 0.6195, "4": 0.0535, "3": 0.2314, "6": 0.0449, "5": 0.0306, "2": 0.0201}, "2": {"1": 0.3657, "6": 0.0395, "4": 0.1768, "3": 0.3399, "5": 0.0744, "2": 0.0038}, "3": {"1": 0.2422, "4": 0.2283, "6": 0.0499, "3": 0.3355, "5": 0.1399, "2": 0.0041}, "4": {"4": 0.218, "1": 0.2071, "3": 0.2925, "6": 0.0714, "5": 0.2087, "2": 0.0023}, "5": {"1": 0.2166, "5": 0.2502, "6": 0.1156, "4": 0.1838, "3": 0.2312, "2": 0.0026}, "6": {"1": 0.2452, "6": 0.2328, "4": 0.1384, "5": 0.187, "3": 0.1937, "2": 0.0029}}}, {"model": "mistralai/Mistral-7B-Instruct-v0.3", "avg_exact": 0.193121, "avg_wp": 0.369178, "avg_bias": 0.1323, "avg_parsed": 0.997591, "avg_mae": 1.623, "total": 7472, "lang_exact": {"ab": 0.168539, "cn": 0.169173, "cy": 0.150313, "de": 0.245931, "en": 0.238979, "es": 0.302632, "eu": 0.047486, "fr": 0.247689, "gl": 0.246606, "he": 0.182448, "hi": 0.2, "ir": 0.158763, "kz": 0.025974, "la": 0.154412, "pl": 0.197417, "sl": 0.152475, "uk": 0.225058}, "lang_wp": {"ab": 0.344101, "cn": 0.332707, "cy": 0.275574, "de": 0.443942, "en": 0.406032, "es": 0.538534, "eu": 0.166201, "fr": 0.471349, "gl": 0.421946, "he": 0.382217, "hi": 0.371134, "ir": 0.262887, "kz": 0.145022, "la": 0.378676, "pl": 0.392066, "sl": 0.309901, "uk": 0.445476}, "lang_parsed": {"ab": 0.997191, "cn": 0.99812, "cy": 0.995825, "de": 1.0, "en": 1.0, "es": 0.99812, "eu": 1.0, "fr": 0.998152, "gl": 0.997738, "he": 0.995381, "hi": 0.991753, "ir": 1.0, "kz": 1.0, "la": 0.992647, "pl": 0.994465, "sl": 0.99802, "uk": 1.0}, "lang_mae": {"ab": 1.4479, "cn": 1.7458, "cy": 2.153, "de": 1.3526, "en": 1.3944, "es": 1.0113, "eu": 2.7793, "fr": 1.1426, "gl": 1.3401, "he": 1.3573, "hi": 1.605, "ir": 2.2742, "kz": 2.619, "la": 1.7704, "pl": 1.4026, "sl": 1.8571, "uk": 1.2645}, "confusion": {"1": {"3": 0.349, "4": 0.1004, "1": 0.2542, "2": 0.0675, "6": 0.0328, "5": 0.1961}, "2": {"3": 0.267, "1": 0.2477, "4": 0.1356, "2": 0.0178, "5": 0.3055, "6": 0.0264}, "3": {"3": 0.2143, "4": 0.1555, "5": 0.3973, "1": 0.1964, "6": 0.0298, "2": 0.0067}, "4": {"1": 0.228, "3": 0.1669, "4": 0.1108, "5": 0.4425, "6": 0.0447, "2": 0.0071}, "5": {"3": 0.1017, "5": 0.5232, "4": 0.118, "1": 0.2018, "6": 0.0504, "2": 0.0049}, "6": {"5": 0.5517, "4": 0.0905, "3": 0.0875, "1": 0.1988, "6": 0.0596, "2": 0.0119}}}, {"model": "utter-project/EuroLLM-9B-Instruct-2512", "avg_exact": 0.231279, "avg_wp": 0.366884, "avg_bias": 0.3921, "avg_parsed": 0.99528, "avg_mae": 1.7804, "total": 7839, "lang_exact": {"ab": 0.3, "cn": 0.311808, "cy": 0.171488, "de": 0.145614, "en": 0.200461, "es": 0.340111, "eu": 0.032609, "fr": 0.297101, "gl": 0.192233, "he": 0.251732, "hi": 0.234317, "ir": 0.260194, "kz": 0.088983, "la": 0.503597, "pl": 0.251337, "sl": 0.196154, "uk": 0.21663}, "lang_wp": {"ab": 0.44186, "cn": 0.48155, "cy": 0.320248, "de": 0.229825, "en": 0.357143, "es": 0.487985, "eu": 0.139946, "fr": 0.449275, "gl": 0.317476, "he": 0.39261, "hi": 0.333948, "ir": 0.395146, "kz": 0.305085, "la": 0.589928, "pl": 0.350267, "sl": 0.356731, "uk": 0.364333}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 0.981405, "de": 1.0, "en": 0.997696, "es": 1.0, "eu": 0.986413, "fr": 0.994565, "gl": 1.0, "he": 1.0, "hi": 0.99262, "ir": 0.970874, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.5535, "cn": 1.2177, "cy": 1.8737, "de": 2.5544, "en": 1.6721, "es": 1.2736, "eu": 2.9063, "fr": 1.4536, "gl": 1.9301, "he": 1.6467, "hi": 2.026, "ir": 1.658, "kz": 1.7797, "la": 1.2302, "pl": 1.9501, "sl": 1.6308, "uk": 1.733}, "confusion": {"1": {"3": 0.0755, "1": 0.558, "6": 0.2072, "2": 0.0534, "5": 0.081, "4": 0.0249}, "3": {"1": 0.238, "6": 0.3483, "5": 0.164, "3": 0.188, "2": 0.0348, "4": 0.0269}, "2": {"3": 0.1518, "1": 0.3181, "2": 0.0485, "6": 0.3167, "5": 0.1282, "4": 0.0367}, "4": {"6": 0.4043, "3": 0.1652, "2": 0.0339, "1": 0.2163, "4": 0.0249, "5": 0.1555}, "5": {"6": 0.505, "5": 0.1523, "3": 0.1188, "2": 0.0267, "1": 0.1828, "4": 0.0145}, "6": {"3": 0.0846, "6": 0.5656, "5": 0.1401, "2": 0.0097, "1": 0.1868, "4": 0.0132}}}, {"model": "allenai/Olmo-3-7B-Instruct", "avg_exact": 0.188459, "avg_wp": 0.346885, "avg_bias": 0.4658, "avg_parsed": 0.991082, "avg_mae": 1.6684, "total": 7625, "lang_exact": {"ab": 0.157068, "cn": 0.192453, "cy": 0.177551, "de": 0.158929, "en": 0.281659, "es": 0.231481, "eu": 0.146341, "fr": 0.158182, "gl": 0.146881, "he": 0.186364, "hi": 0.186613, "ir": 0.198381, "kz": 0.208531, "la": 0.178571, "pl": 0.218978, "sl": 0.162745, "uk": 0.210654}, "lang_wp": {"ab": 0.331152, "cn": 0.340566, "cy": 0.331633, "de": 0.298214, "en": 0.451965, "es": 0.397222, "eu": 0.345528, "fr": 0.304545, "gl": 0.274648, "he": 0.364773, "hi": 0.334686, "ir": 0.362348, "kz": 0.327014, "la": 0.271429, "pl": 0.404197, "sl": 0.327451, "uk": 0.376513}, "lang_parsed": {"ab": 0.989529, "cn": 1.0, "cy": 1.0, "de": 0.989286, "en": 0.982533, "es": 0.996296, "eu": 1.0, "fr": 1.0, "gl": 0.981891, "he": 1.0, "hi": 0.933063, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 0.988235, "uk": 1.0}, "lang_mae": {"ab": 1.5714, "cn": 1.8151, "cy": 1.6755, "de": 1.8935, "en": 1.3, "es": 1.4963, "eu": 1.5962, "fr": 1.9036, "gl": 2.0574, "he": 1.5409, "hi": 1.6435, "ir": 1.5243, "kz": 1.5972, "la": 2.2429, "pl": 1.5109, "sl": 1.6448, "uk": 1.5908}, "confusion": {"1": {"3": 0.236, "4": 0.2332, "6": 0.1474, "5": 0.0588, "2": 0.2976, "1": 0.0271}, "2": {"3": 0.2211, "4": 0.233, "6": 0.2091, "5": 0.0575, "2": 0.273, "1": 0.0063}, "3": {"3": 0.1794, "5": 0.0816, "4": 0.2353, "2": 0.2412, "6": 0.261, "1": 0.0015}, "4": {"3": 0.1615, "4": 0.2148, "6": 0.3001, "5": 0.0775, "2": 0.2411, "1": 0.005}, "5": {"6": 0.3787, "3": 0.1346, "4": 0.1886, "2": 0.2224, "5": 0.0709, "1": 0.0048}, "6": {"4": 0.208, "6": 0.3656, "3": 0.1273, "5": 0.0807, "2": 0.207, "1": 0.0114}}}, {"model": "swiss-ai/Apertus-8B-Instruct-2509", "avg_exact": 0.209399, "avg_wp": 0.345723, "avg_bias": -0.0463, "avg_parsed": 0.960564, "avg_mae": 1.7953, "total": 7937, "lang_exact": {"ab": 0.183258, "cn": 0.194805, "cy": 0.17551, "de": 0.221831, "en": 0.28, "es": 0.278598, "eu": 0.132979, "fr": 0.289568, "gl": 0.161793, "he": 0.186139, "hi": 0.190388, "ir": 0.142857, "kz": 0.015625, "la": 0.468531, "pl": 0.258123, "sl": 0.250485, "uk": 0.182222}, "lang_wp": {"ab": 0.279412, "cn": 0.317254, "cy": 0.330612, "de": 0.363556, "en": 0.468889, "es": 0.444649, "eu": 0.295213, "fr": 0.493705, "gl": 0.270955, "he": 0.30099, "hi": 0.278189, "ir": 0.259557, "kz": 0.105469, "la": 0.517483, "pl": 0.364621, "sl": 0.412621, "uk": 0.35}, "lang_parsed": {"ab": 0.963801, "cn": 0.998145, "cy": 0.971429, "de": 0.973592, "en": 0.997778, "es": 0.99262, "eu": 0.989362, "fr": 0.98741, "gl": 0.844055, "he": 0.883168, "hi": 0.992606, "ir": 0.995976, "kz": 0.730469, "la": 0.993007, "pl": 0.998195, "sl": 0.98835, "uk": 0.935556}, "lang_mae": {"ab": 2.2887, "cn": 1.9758, "cy": 1.7815, "de": 1.6799, "en": 1.3229, "es": 1.3736, "eu": 2.0672, "fr": 1.1275, "gl": 1.9215, "he": 1.8296, "hi": 2.3296, "ir": 2.1475, "kz": 2.6898, "la": 1.5775, "pl": 1.8445, "sl": 1.444, "uk": 1.6793}, "confusion": {"1": {"1": 0.479, "6": 0.1789, "3": 0.1817, "4": 0.1025, "2": 0.0391, "5": 0.0186}, "2": {"1": 0.399, "4": 0.0827, "6": 0.2372, "3": 0.1963, "2": 0.0374, "5": 0.0474}, "3": {"1": 0.3447, "4": 0.1127, "6": 0.2454, "3": 0.1913, "5": 0.0808, "2": 0.0252}, "4": {"1": 0.3366, "6": 0.3113, "5": 0.0986, "4": 0.0915, "3": 0.1472, "2": 0.0148}, "5": {"1": 0.2924, "4": 0.0918, "5": 0.1516, "6": 0.3554, "3": 0.0956, "2": 0.0132}, "6": {"1": 0.2443, "6": 0.4643, "5": 0.1665, "3": 0.0643, "2": 0.0072, "4": 0.0534}}}, {"model": "speakleash/Bielik-4.5B-v3.0-Instruct", "avg_exact": 0.180949, "avg_wp": 0.329994, "avg_bias": 0.5962, "avg_parsed": 0.998459, "avg_mae": 1.8388, "total": 6488, "lang_exact": {"ab": 0.106557, "cn": 0.128821, "cy": 0.170213, "de": 0.186312, "en": 0.220513, "es": 0.193294, "eu": 0.119658, "fr": 0.242126, "gl": 0.210773, "he": 0.126154, "hi": 0.172996, "ir": 0.138593, "kz": 0.114035, "la": 0.38806, "pl": 0.270318, "sl": 0.150905, "uk": 0.120755}, "lang_wp": {"ab": 0.241803, "cn": 0.274017, "cy": 0.309574, "de": 0.327947, "en": 0.430769, "es": 0.342209, "eu": 0.316239, "fr": 0.370079, "gl": 0.380562, "he": 0.253846, "hi": 0.305907, "ir": 0.283582, "kz": 0.25, "la": 0.537313, "pl": 0.415194, "sl": 0.299799, "uk": 0.237736}, "lang_parsed": {"ab": 0.995902, "cn": 0.995633, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 0.997658, "he": 0.996923, "hi": 1.0, "ir": 1.0, "kz": 0.991228, "la": 1.0, "pl": 0.9947, "sl": 1.0, "uk": 0.996226}, "lang_mae": {"ab": 2.2346, "cn": 1.9846, "cy": 1.9851, "de": 1.8327, "en": 1.2538, "es": 1.789, "eu": 1.9373, "fr": 1.752, "gl": 1.5235, "he": 2.108, "hi": 2.1097, "ir": 2.0192, "kz": 2.1858, "la": 1.4254, "pl": 1.4813, "sl": 1.9577, "uk": 2.1856}, "confusion": {"1": {"1": 0.3137, "5": 0.6027, "2": 0.0083, "3": 0.0227, "4": 0.0227, "6": 0.0299}, "2": {"1": 0.2562, "5": 0.6172, "4": 0.0652, "3": 0.0357, "2": 0.021, "6": 0.0047}, "3": {"1": 0.1879, "5": 0.6958, "2": 0.0166, "4": 0.0707, "3": 0.0233, "6": 0.0058}, "4": {"1": 0.1923, "5": 0.6846, "4": 0.075, "6": 0.0147, "3": 0.0212, "2": 0.0122}, "5": {"5": 0.6783, "4": 0.0909, "1": 0.1868, "3": 0.028, "6": 0.009, "2": 0.007}, "6": {"5": 0.6063, "1": 0.2114, "4": 0.0975, "3": 0.0215, "2": 0.0076, "6": 0.0557}}}, {"model": "speakleash/Bielik-1.5B-v3.0-Instruct", "avg_exact": 0.145808, "avg_wp": 0.242679, "avg_bias": -1.8483, "avg_parsed": 0.908292, "avg_mae": 2.2702, "total": 6488, "lang_exact": {"ab": 0.217213, "cn": 0.196507, "cy": 0.125532, "de": 0.06654, "en": 0.069231, "es": 0.142012, "eu": 0.017094, "fr": 0.173228, "gl": 0.056206, "he": 0.218462, "hi": 0.223629, "ir": 0.164179, "kz": 0.052632, "la": 0.186567, "pl": 0.233216, "sl": 0.185111, "uk": 0.135849}, "lang_wp": {"ab": 0.331967, "cn": 0.298035, "cy": 0.228723, "de": 0.080798, "en": 0.153846, "es": 0.224852, "eu": 0.131054, "fr": 0.267717, "gl": 0.160422, "he": 0.323077, "hi": 0.333333, "ir": 0.267591, "kz": 0.201754, "la": 0.19403, "pl": 0.366608, "sl": 0.279678, "uk": 0.292453}, "lang_parsed": {"ab": 0.995902, "cn": 0.991266, "cy": 1.0, "de": 0.186312, "en": 0.833333, "es": 0.846154, "eu": 1.0, "fr": 0.992126, "gl": 0.995316, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 0.982332, "sl": 0.995976, "uk": 0.996226}, "lang_mae": {"ab": 2.107, "cn": 2.0595, "cy": 2.4064, "de": 1.8061, "en": 2.3138, "es": 2.3869, "eu": 2.9402, "fr": 2.2599, "gl": 2.6471, "he": 1.9138, "hi": 2.0717, "ir": 2.2345, "kz": 2.4035, "la": 3.3881, "pl": 1.8345, "sl": 2.2505, "uk": 2.0}, "confusion": {"1": {"1": 0.8964, "3": 0.0045, "4": 0.0011, "6": 0.0724, "5": 0.0245, "2": 0.0011}, "2": {"1": 0.916, "2": 0.0009, "6": 0.042, "4": 0.0026, "5": 0.0377, "3": 0.0009}, "3": {"1": 0.8989, "2": 0.0064, "5": 0.0441, "3": 0.0028, "4": 0.0055, "6": 0.0423}, "4": {"1": 0.9007, "2": 0.0027, "6": 0.0537, "5": 0.042, "4": 0.0009}, "5": {"1": 0.8473, "2": 0.0022, "6": 0.0841, "5": 0.0619, "4": 0.0044}, "6": {"1": 0.8203, "6": 0.1114, "5": 0.0641, "2": 0.0028, "3": 0.0014}}}, {"model": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "avg_exact": 0.082031, "avg_wp": 0.116211, "avg_bias": -2.0261, "avg_parsed": 0.449219, "avg_mae": 2.4957, "total": 512, "lang_exact": {"ab": 0.065909, "cn": 0.180556}, "lang_wp": {"ab": 0.104545, "cn": 0.1875}, "lang_parsed": {"ab": 0.475, "cn": 0.291667}, "lang_mae": {"ab": 2.6172, "cn": 1.2857}, "confusion": {"1": {"1": 0.766, "6": 0.0638, "5": 0.0851, "2": 0.0213, "4": 0.0426, "3": 0.0213}, "2": {"1": 0.8108, "5": 0.0541, "3": 0.0541, "2": 0.0811}, "3": {"1": 0.8684, "3": 0.0789, "5": 0.0263, "4": 0.0263}, "4": {"1": 0.9459, "6": 0.027, "5": 0.027}, "5": {"1": 1.0}, "6": {"1": 0.9487, "4": 0.0256, "2": 0.0256}}}];
|
| 296 |
const ALL_LANGS_2 = ["ab", "eu", "cn", "en", "fr", "gl", "de", "he", "hi", "ir", "kz", "la", "pl", "sl", "es", "uk", "cy"];
|
| 297 |
const LANG_COUNTS_2 = {"ab": 600, "cn": 600, "cy": 560, "de": 600, "en": 521, "es": 600, "eu": 462, "fr": 600, "gl": 520, "he": 600, "hi": 600, "ir": 582, "kz": 328, "la": 189, "pl": 600, "sl": 600, "uk": 530};
|
| 298 |
const LANG_DIST_2 = {"ab": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "cn": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "cy": {"1": 60, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "de": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "en": {"1": 21, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "es": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "eu": {"1": 10, "2": 100, "3": 52, "4": 100, "5": 100, "6": 100}, "fr": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "gl": {"1": 20, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "he": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "hi": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "ir": {"1": 82, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "kz": {"1": 6, "2": 53, "3": 37, "4": 100, "5": 100, "6": 32}, "la": {"1": 34, "2": 3, "3": 3, "4": 35, "5": 14, "6": 100}, "pl": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "sl": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "uk": {"1": 40, "2": 100, "3": 90, "4": 100, "5": 100, "6": 100}};
|
| 299 |
-
const TOTAL_PREDS_2 =
|
| 300 |
|
| 301 |
function langName(c) { return LANG_NAMES[c] || c.toUpperCase(); }
|
| 302 |
|
|
@@ -318,7 +318,7 @@
|
|
| 318 |
function dsLangs() { return activeDS === 1 ? ALL_LANGS : ALL_LANGS_2; }
|
| 319 |
function dsLangCounts() { return activeDS === 1 ? LANG_COUNTS : LANG_COUNTS_2; }
|
| 320 |
function dsLangDist() { return activeDS === 1 ? LANG_DIST : LANG_DIST_2; }
|
| 321 |
-
function dsTotalPreds() { return activeDS === 1 ?
|
| 322 |
|
| 323 |
window.setDataset = function(ds) {
|
| 324 |
if (ds === 2 && !HAS_SECOND) return;
|
|
@@ -493,7 +493,7 @@
|
|
| 493 |
}).join('');
|
| 494 |
|
| 495 |
document.getElementById('footer').textContent =
|
| 496 |
-
`
|
| 497 |
}
|
| 498 |
|
| 499 |
// ── dataset distribution ──
|
|
|
|
| 284 |
|
| 285 |
<script>
|
| 286 |
(function() {
|
| 287 |
+
const ALL_ROWS = [{"model": "meta-llama/Llama-3.3-70B-Instruct", "avg_exact": 0.344137, "avg_wp": 0.473008, "avg_bias": 0.9363, "avg_parsed": 0.991466, "avg_mae": 1.2753, "total": 10429, "lang_exact": {"ab": 0.231667, "ar": 0.46, "az": 0.3375, "be": 0.355, "bg": 0.334254, "bo": 0.535, "ca": 0.309192, "cn": 0.356667, "cs": 0.5125, "cy": 0.253333, "da": 0.3675, "de": 0.315, "el": 0.38, "en": 0.355, "es": 0.384384, "et": 0.525, "eu": 0.207705, "fa": 0.341667, "fi": 0.4425, "fr": 0.390052, "gl": 0.203333, "he": 0.261745}, "lang_wp": {"ab": 0.388333, "ar": 0.54375, "az": 0.4525, "be": 0.48, "bg": 0.455801, "bo": 0.60375, "ca": 0.416435, "cn": 0.490833, "cs": 0.58, "cy": 0.445833, "da": 0.485, "de": 0.453333, "el": 0.49125, "en": 0.4775, "es": 0.432432, "et": 0.63, "eu": 0.393635, "fa": 0.499167, "fi": 0.55875, "fr": 0.459424, "gl": 0.374167, "he": 0.430369}, "lang_parsed": {"ab": 0.966667, "ar": 1.0, "az": 1.0, "be": 1.0, "bg": 1.0, "bo": 1.0, "ca": 0.997214, "cn": 1.0, "cs": 0.9925, "cy": 1.0, "da": 0.9925, "de": 0.998333, "el": 1.0, "en": 0.931667, "es": 0.975976, "et": 1.0, "eu": 1.0, "fa": 1.0, "fi": 1.0, "fr": 0.992147, "gl": 0.985, "he": 1.0}, "lang_mae": {"ab": 1.5672, "ar": 1.21, "az": 1.4625, "be": 1.3975, "bg": 1.2707, "bo": 0.9225, "ca": 1.3883, "cn": 1.2117, "cs": 0.9597, "cy": 1.2617, "da": 1.3375, "de": 1.227, "el": 1.2775, "en": 1.1574, "es": 1.44, "et": 0.815, "eu": 1.4456, "fa": 1.16, "fi": 0.9925, "fr": 1.4459, "gl": 1.5939, "he": 1.3339}, "confusion": {"1": {"4": 0.4673, "5": 0.0977, "1": 0.3257, "2": 0.0818, "6": 0.0051, "3": 0.0224}, "2": {"5": 0.3272, "4": 0.5801, "1": 0.0427, "6": 0.0119, "2": 0.0289, "3": 0.0092}, "3": {"4": 0.2687, "5": 0.6474, "1": 0.0556, "6": 0.0283}, "4": {"5": 0.7847, "1": 0.0316, "4": 0.1342, "6": 0.0496}, "5": {"6": 0.1107, "5": 0.8501, "1": 0.0087, "4": 0.0305}, "6": {"6": 0.4103, "5": 0.5625, "4": 0.0165, "1": 0.0107}}}, {"model": "CYFRAGOVPL/Llama-PLLuM-70B-chat-250801", "avg_exact": 0.198888, "avg_wp": 0.302751, "avg_bias": -1.8854, "avg_parsed": 0.762026, "avg_mae": 2.0714, "total": 21952, "lang_exact": {"ab": 0.045, "ar": 0.2225, "az": 0.26, "be": 0.235, "bg": 0.21547, "bo": 0.3275, "ca": 0.144847, "cn": 0.2, "cs": 0.25, "cy": 0.233333, "da": 0.2, "de": 0.163333, "el": 0.1875, "en": 0.135, "es": 0.114114, "et": 0.25, "eu": 0.132328, "fa": 0.288333, "fi": 0.24, "fr": 0.230366, "gl": 0.135, "he": 0.08, "hi": 0.176471, "hu": 0.1175, "hv": 0.4075, "ir": 0.275, "is": 0.3425, "it": 0.13, "ka": 0.031447, "kz": 0.095, "la": 0.350877, "li": 0.2425, "lv": 0.23, "mk": 0.1925, "mt": 0.2425, "nl": 0.2225, "no": 0.1725, "pl": 0.077193, "pt": 0.2075, "ro": 0.225, "ru": 0.166667, "sk": 0.16, "sl": 0.2475, "sq": 0.245, "sr": 0.2675, "sv": 0.24, "tr": 0.235, "uk": 0.158537}, "lang_wp": {"ab": 0.0625, "ar": 0.40125, "az": 0.39375, "be": 0.35, "bg": 0.319061, "bo": 0.47125, "ca": 0.232591, "cn": 0.291667, "cs": 0.36125, "cy": 0.344167, "da": 0.3125, "de": 0.2475, "el": 0.2675, "en": 0.230833, "es": 0.15015, "et": 0.38125, "eu": 0.201005, "fa": 0.458333, "fi": 0.3525, "fr": 0.332461, "gl": 0.205, "he": 0.144167, "hi": 0.286765, "hu": 0.13875, "hv": 0.57, "ir": 0.439167, "is": 0.57, "it": 0.18375, "ka": 0.157233, "kz": 0.145833, "la": 0.519493, "li": 0.36125, "lv": 0.355, "mk": 0.2825, "mt": 0.39125, "nl": 0.355, "no": 0.2575, "pl": 0.103509, "pt": 0.30875, "ro": 0.34375, "ru": 0.238333, "sk": 0.22625, "sl": 0.3675, "sq": 0.36625, "sr": 0.4175, "sv": 0.3625, "tr": 0.3525, "uk": 0.232578}, "lang_parsed": {"ab": 0.16, "ar": 0.785, "az": 0.94, "be": 0.9275, "bg": 0.801105, "bo": 0.875, "ca": 0.62117, "cn": 0.751667, "cs": 0.7525, "cy": 0.806667, "da": 0.925, "de": 0.958333, "el": 0.69, "en": 0.848333, "es": 0.228228, "et": 1.0, "eu": 0.716918, "fa": 0.878333, "fi": 0.905, "fr": 0.730366, "gl": 0.651667, "he": 0.346667, "hi": 0.851103, "hu": 0.205, "hv": 0.9525, "ir": 0.973333, "is": 0.99, "it": 0.4, "ka": 0.889937, "kz": 0.77, "la": 1.0, "li": 0.9725, "lv": 0.945, "mk": 0.6475, "mt": 0.845, "nl": 0.9225, "no": 0.71, "pl": 0.354386, "pt": 0.82, "ro": 0.955, "ru": 0.843333, "sk": 0.5525, "sl": 0.69, "sq": 0.9825, "sr": 0.8825, "sv": 0.98, "tr": 0.575, "uk": 0.778746}, "lang_mae": {"ab": 1.9271, "ar": 1.2962, "az": 2.1011, "be": 2.4798, "bg": 2.3138, "bo": 1.6314, "ca": 2.3946, "cn": 1.8271, "cs": 1.8771, "cy": 1.6756, "da": 2.6757, "de": 2.4417, "el": 2.4565, "en": 2.2318, "es": 1.0789, "et": 2.3775, "eu": 2.3762, "fa": 1.1917, "fi": 2.4144, "fr": 2.0036, "gl": 2.2558, "he": 1.5, "hi": 1.8553, "hu": 1.2439, "hv": 1.3307, "ir": 1.4366, "is": 0.9697, "it": 2.0812, "ka": 3.318, "kz": 2.8117, "la": 1.2768, "li": 2.5244, "lv": 2.4392, "mk": 2.1969, "mt": 1.7337, "nl": 2.2222, "no": 2.5634, "pl": 2.5, "pt": 2.4238, "ro": 2.5524, "ru": 2.3735, "sk": 2.362, "sl": 1.6014, "sq": 2.5064, "sr": 1.8499, "sv": 2.5128, "tr": 1.1783, "uk": 2.2416}, "confusion": {"1": {"1": 0.937, "3": 0.0359, "4": 0.0138, "5": 0.0091, "2": 0.0023, "6": 0.0018}, "2": {"1": 0.8948, "3": 0.0594, "5": 0.0169, "4": 0.0218, "2": 0.0038, "6": 0.0033}, "3": {"3": 0.1034, "5": 0.0575, "1": 0.7883, "4": 0.0508}, "4": {"1": 0.725, "5": 0.0808, "4": 0.1107, "3": 0.0756, "6": 0.007, "2": 0.0009}, "5": {"1": 0.7925, "5": 0.1018, "4": 0.072, "3": 0.0198, "6": 0.0125, "2": 0.0014}, "6": {"6": 0.0448, "1": 0.741, "5": 0.1486, "4": 0.0539, "3": 0.0111, "2": 0.0006}}}, {"model": "CYFRAGOVPL/pllum-12b-nc-chat-250715", "avg_exact": 0.14764, "avg_wp": 0.236994, "avg_bias": -0.8839, "avg_parsed": 0.635887, "avg_mae": 2.0278, "total": 21952, "lang_exact": {"ab": 0.193333, "ar": 0.055, "az": 0.1525, "be": 0.2525, "bg": 0.121547, "bo": 0.3325, "ca": 0.197772, "cn": 0.103333, "cs": 0.15, "cy": 0.101667, "da": 0.15, "de": 0.155, "el": 0.165, "en": 0.186667, "es": 0.234234, "et": 0.195, "eu": 0.060302, "fa": 0.166667, "fi": 0.1125, "fr": 0.167539, "gl": 0.098333, "he": 0.168333, "hi": 0.079044, "hu": 0.1675, "hv": 0.3, "ir": 0.103333, "is": 0.185, "it": 0.1625, "ka": 0.031447, "kz": 0.115, "la": 0.126706, "li": 0.1625, "lv": 0.1425, "mk": 0.0875, "mt": 0.1425, "nl": 0.1425, "no": 0.135, "pl": 0.087719, "pt": 0.0425, "ro": 0.1925, "ru": 0.2, "sk": 0.13, "sl": 0.19, "sq": 0.085, "sr": 0.195, "sv": 0.12, "tr": 0.2375, "uk": 0.123693}, "lang_wp": {"ab": 0.323333, "ar": 0.09, "az": 0.29125, "be": 0.36625, "bg": 0.18232, "bo": 0.4775, "ca": 0.292479, "cn": 0.159167, "cs": 0.22625, "cy": 0.185, "da": 0.26625, "de": 0.264167, "el": 0.25875, "en": 0.2875, "es": 0.340841, "et": 0.305, "eu": 0.103015, "fa": 0.304167, "fi": 0.18875, "fr": 0.311518, "gl": 0.165, "he": 0.239167, "hi": 0.129596, "hu": 0.27125, "hv": 0.4275, "ir": 0.150833, "is": 0.26, "it": 0.2425, "ka": 0.055031, "kz": 0.1875, "la": 0.251462, "li": 0.24375, "lv": 0.25875, "mk": 0.1425, "mt": 0.2225, "nl": 0.23125, "no": 0.22375, "pl": 0.118421, "pt": 0.09375, "ro": 0.335, "ru": 0.315833, "sk": 0.2375, "sl": 0.31125, "sq": 0.15625, "sr": 0.30375, "sv": 0.17625, "tr": 0.35875, "uk": 0.204704}, "lang_parsed": {"ab": 0.906667, "ar": 0.2325, "az": 0.8225, "be": 0.76, "bg": 0.444751, "bo": 0.785, "ca": 0.810585, "cn": 0.565, "cs": 0.5875, "cy": 0.77, "da": 0.7, "de": 0.7, "el": 0.7725, "en": 0.771667, "es": 0.702703, "et": 0.7275, "eu": 0.356784, "fa": 0.845, "fi": 0.5475, "fr": 0.719895, "gl": 0.435, "he": 0.651667, "hi": 0.505515, "hu": 0.75, "hv": 0.7675, "ir": 0.591667, "is": 0.6175, "it": 0.6525, "ka": 0.267296, "kz": 0.671667, "la": 0.810916, "li": 0.695, "lv": 0.68, "mk": 0.3775, "mt": 0.655, "nl": 0.5875, "no": 0.6975, "pl": 0.224561, "pt": 0.28, "ro": 0.8975, "ru": 0.856667, "sk": 0.6725, "sl": 0.705, "sq": 0.3675, "sr": 0.5825, "sv": 0.4275, "tr": 0.8325, "uk": 0.609756}, "lang_mae": {"ab": 1.9062, "ar": 2.1505, "az": 2.0091, "be": 1.7401, "bg": 1.9441, "bo": 1.1274, "ca": 2.4502, "cn": 2.2183, "cs": 2.1702, "cy": 2.4134, "da": 2.0429, "de": 1.6976, "el": 2.6472, "en": 1.8488, "es": 1.6667, "et": 1.9794, "eu": 2.2347, "fa": 1.6292, "fi": 2.0822, "fr": 1.9382, "gl": 1.659, "he": 1.9412, "hi": 2.2945, "hu": 2.4667, "hv": 1.4397, "ir": 2.4254, "is": 2.0688, "it": 1.9885, "ka": 3.1412, "kz": 2.3027, "la": 2.1611, "li": 2.5899, "lv": 2.1618, "mk": 1.9007, "mt": 2.0191, "nl": 1.983, "no": 2.6022, "pl": 1.4531, "pt": 2.2411, "ro": 2.1866, "ru": 1.8502, "sk": 2.4201, "sl": 1.6135, "sq": 1.9184, "sr": 1.4807, "sv": 2.2339, "tr": 1.982, "uk": 1.8629}, "confusion": {"1": {"1": 0.6392, "4": 0.0704, "6": 0.1123, "2": 0.0827, "3": 0.0693, "5": 0.026}, "2": {"1": 0.5435, "3": 0.0779, "6": 0.1307, "2": 0.0921, "5": 0.0406, "4": 0.1153}, "3": {"3": 0.0514, "5": 0.0706, "6": 0.2046, "1": 0.4667, "4": 0.1623, "2": 0.0444}, "4": {"5": 0.0957, "1": 0.4275, "6": 0.2332, "4": 0.1526, "2": 0.0294, "3": 0.0616}, "5": {"6": 0.1433, "1": 0.5006, "2": 0.0101, "4": 0.163, "5": 0.1612, "3": 0.0218}, "6": {"6": 0.1611, "1": 0.5411, "5": 0.1366, "4": 0.1172, "2": 0.0227, "3": 0.0212}}}];
|
| 288 |
const ALL_LANGS = ["sq", "ab", "ar", "az", "eu", "be", "bo", "bg", "ca", "cn", "hv", "cs", "da", "nl", "en", "et", "fa", "fi", "fr", "gl", "ka", "de", "el", "he", "hi", "hu", "is", "ir", "it", "kz", "la", "lv", "li", "mk", "mt", "no", "pl", "pt", "ro", "ru", "sr", "sk", "sl", "es", "sv", "tr", "uk", "cy"];
|
| 289 |
const LANG_NAMES = {"af": "Afrikaans", "ab": "Arabic", "az": "Azerbaijani", "ar": "Armenian", "be": "Belarusian", "bo": "Bosnian", "bg": "Bulgarian", "bn": "Brunei", "ca": "Catalan", "cs": "Czech", "cn": "Chinese", "cy": "Welsh", "da": "Danish", "de": "German", "el": "Greek", "en": "English", "eo": "Esperanto", "es": "Spanish", "et": "Estonian", "eu": "Basque", "fa": "Faroese", "fi": "Finnish", "fr": "French", "ga": "Irish", "gl": "Galician", "gu": "Gujarati", "he": "Hebrew", "hi": "Hindi", "hr": "Croatian", "hu": "Hungarian", "hv": "Croatia", "id": "Indonesian", "is": "Icelandic", "it": "Italian", "ir": "Irish", "ja": "Japanese", "ka": "Georgian", "kz": "Kazakh", "km": "Khmer", "kn": "Kannada", "ko": "Korean", "la": "Latin", "li": "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", "pe": "Persian", "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"};
|
| 290 |
const LANG_COUNTS = {"ab": 600, "ar": 400, "az": 400, "be": 400, "bg": 362, "bo": 400, "ca": 359, "cn": 600, "cs": 400, "cy": 600, "da": 400, "de": 600, "el": 400, "en": 600, "es": 333, "et": 400, "eu": 597, "fa": 600, "fi": 400, "fr": 382, "gl": 600, "he": 600, "hi": 544, "hu": 400, "hv": 400, "ir": 600, "is": 400, "it": 400, "ka": 318, "kz": 600, "la": 513, "li": 400, "lv": 400, "mk": 400, "mt": 400, "nl": 400, "no": 400, "pl": 571, "pt": 400, "ro": 400, "ru": 600, "sk": 400, "sl": 400, "sq": 400, "sr": 400, "sv": 400, "tr": 400, "uk": 574};
|
|
|
|
| 292 |
|
| 293 |
// second dataset
|
| 294 |
const HAS_SECOND = true;
|
| 295 |
+
const ALL_ROWS_2 = [{"model": "allenai/Olmo-3.1-32B-Instruct", "avg_exact": 0.312393, "avg_wp": 0.507738, "avg_bias": 0.4911, "avg_parsed": 0.999475, "avg_mae": 1.1207, "total": 7625, "lang_exact": {"ab": 0.295812, "cn": 0.377358, "cy": 0.277551, "de": 0.314286, "en": 0.39083, "es": 0.314815, "eu": 0.281843, "fr": 0.356364, "gl": 0.309859, "he": 0.227273, "hi": 0.249493, "ir": 0.271255, "kz": 0.189573, "la": 0.435714, "pl": 0.377737, "sl": 0.345098, "uk": 0.273608}, "lang_wp": {"ab": 0.485602, "cn": 0.600943, "cy": 0.50102, "de": 0.516071, "en": 0.601528, "es": 0.528704, "eu": 0.501355, "fr": 0.544545, "gl": 0.482897, "he": 0.422727, "hi": 0.447262, "ir": 0.446356, "kz": 0.386256, "la": 0.457143, "pl": 0.555657, "sl": 0.521569, "uk": 0.495157}, "lang_parsed": {"ab": 0.997382, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 0.998182, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 0.996078, "uk": 1.0}, "lang_mae": {"ab": 1.252, "cn": 0.8623, "cy": 1.102, "de": 1.0893, "en": 0.8908, "es": 0.9907, "eu": 1.1274, "fr": 1.0055, "gl": 1.169, "he": 1.3409, "hi": 1.2373, "ir": 1.2449, "kz": 1.4787, "la": 1.9714, "pl": 1.0018, "sl": 1.1043, "uk": 1.0944}, "confusion": {"1": {"1": 0.3559, "3": 0.3783, "6": 0.0437, "2": 0.0353, "4": 0.1608, "5": 0.026}, "2": {"1": 0.1208, "3": 0.426, "4": 0.2703, "5": 0.0691, "6": 0.0887, "2": 0.0251}, "3": {"3": 0.3674, "2": 0.011, "4": 0.3909, "5": 0.1242, "6": 0.0742, "1": 0.0323}, "4": {"3": 0.2456, "4": 0.3828, "6": 0.1464, "5": 0.1992, "1": 0.026}, "5": {"6": 0.289, "5": 0.34, "4": 0.2492, "3": 0.1083, "1": 0.0119, "2": 0.0016}, "6": {"5": 0.2819, "6": 0.4577, "4": 0.1805, "3": 0.0502, "1": 0.0288, "2": 0.0009}}}, {"model": "utter-project/EuroLLM-22B-Instruct-2512", "avg_exact": 0.269039, "avg_wp": 0.451716, "avg_bias": -0.0838, "avg_parsed": 0.989284, "avg_mae": 1.3787, "total": 7839, "lang_exact": {"ab": 0.204651, "cn": 0.341328, "cy": 0.216942, "de": 0.319298, "en": 0.299539, "es": 0.301294, "eu": 0.203804, "fr": 0.317029, "gl": 0.192233, "he": 0.26097, "hi": 0.269373, "ir": 0.275728, "kz": 0.271186, "la": 0.172662, "pl": 0.254902, "sl": 0.319231, "uk": 0.238512}, "lang_wp": {"ab": 0.305814, "cn": 0.550738, "cy": 0.391529, "de": 0.528947, "en": 0.498848, "es": 0.474122, "eu": 0.418478, "fr": 0.500906, "gl": 0.375728, "he": 0.413395, "hi": 0.429889, "ir": 0.463107, "kz": 0.491525, "la": 0.503597, "pl": 0.382353, "sl": 0.515385, "uk": 0.446389}, "lang_parsed": {"ab": 0.997674, "cn": 0.994465, "cy": 0.977273, "de": 1.0, "en": 1.0, "es": 0.998152, "eu": 1.0, "fr": 0.990942, "gl": 0.941748, "he": 0.923788, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 2.2168, "cn": 0.9666, "cy": 1.4947, "de": 1.0912, "en": 1.1636, "es": 1.3056, "eu": 1.4375, "fr": 1.1499, "gl": 1.5588, "he": 1.4125, "hi": 1.6144, "ir": 1.3107, "kz": 1.2034, "la": 1.2734, "pl": 1.8164, "sl": 1.1077, "uk": 1.3042}, "confusion": {"2": {"1": 0.4793, "3": 0.0716, "5": 0.3635, "4": 0.0554, "2": 0.0302}, "1": {"1": 0.7788, "2": 0.0221, "3": 0.0498, "5": 0.1143, "4": 0.0332, "6": 0.0018}, "4": {"1": 0.2238, "5": 0.6674, "6": 0.0007, "3": 0.0474, "4": 0.0544, "2": 0.0063}, "3": {"1": 0.3294, "5": 0.5033, "4": 0.0778, "3": 0.0734, "2": 0.0117, "6": 0.0044}, "5": {"1": 0.1667, "5": 0.7823, "6": 0.0046, "4": 0.0282, "3": 0.0175, "2": 0.0008}, "6": {"1": 0.1984, "5": 0.7628, "4": 0.0141, "6": 0.0132, "3": 0.0097, "2": 0.0018}}}, {"model": "cjvt/GaMS3-12B-Instruct", "avg_exact": 0.235073, "avg_wp": 0.386782, "avg_bias": -0.3635, "avg_parsed": 0.886469, "avg_mae": 1.4487, "total": 7989, "lang_exact": {"ab": 0.207675, "cn": 0.25859, "cy": 0.162602, "de": 0.273205, "en": 0.296703, "es": 0.289134, "eu": 0.120321, "fr": 0.304505, "gl": 0.061896, "he": 0.242545, "hi": 0.287796, "ir": 0.163022, "kz": 0.128405, "la": 0.524138, "pl": 0.28777, "sl": 0.228682, "uk": 0.262582}, "lang_wp": {"ab": 0.308126, "cn": 0.43038, "cy": 0.305894, "de": 0.443082, "en": 0.483516, "es": 0.480663, "eu": 0.255348, "fr": 0.461261, "gl": 0.147969, "he": 0.378728, "hi": 0.439891, "ir": 0.332008, "kz": 0.321012, "la": 0.572414, "pl": 0.436151, "sl": 0.361434, "uk": 0.458425}, "lang_parsed": {"ab": 0.875847, "cn": 0.962025, "cy": 0.857724, "de": 0.894921, "en": 0.951648, "es": 1.0, "eu": 0.703209, "fr": 0.927928, "gl": 0.613153, "he": 0.914513, "hi": 0.87796, "ir": 0.998012, "kz": 0.891051, "la": 1.0, "pl": 0.895683, "sl": 0.839147, "uk": 0.894967}, "lang_mae": {"ab": 1.9691, "cn": 1.3759, "cy": 1.6872, "de": 1.182, "en": 1.2055, "es": 1.2615, "eu": 1.4791, "fr": 1.3398, "gl": 2.4132, "he": 1.5739, "hi": 1.2531, "ir": 1.6494, "kz": 1.5153, "la": 1.2966, "pl": 1.3233, "sl": 1.3741, "uk": 1.1051}, "confusion": {"1": {"1": 0.6195, "4": 0.0535, "3": 0.2314, "6": 0.0449, "5": 0.0306, "2": 0.0201}, "2": {"1": 0.3657, "6": 0.0395, "4": 0.1768, "3": 0.3399, "5": 0.0744, "2": 0.0038}, "3": {"1": 0.2422, "4": 0.2283, "6": 0.0499, "3": 0.3355, "5": 0.1399, "2": 0.0041}, "4": {"4": 0.218, "1": 0.2071, "3": 0.2925, "6": 0.0714, "5": 0.2087, "2": 0.0023}, "5": {"1": 0.2166, "5": 0.2502, "6": 0.1156, "4": 0.1838, "3": 0.2312, "2": 0.0026}, "6": {"1": 0.2452, "6": 0.2328, "4": 0.1384, "5": 0.187, "3": 0.1937, "2": 0.0029}}}, {"model": "mistralai/Mistral-7B-Instruct-v0.3", "avg_exact": 0.193121, "avg_wp": 0.369178, "avg_bias": 0.1323, "avg_parsed": 0.997591, "avg_mae": 1.623, "total": 7472, "lang_exact": {"ab": 0.168539, "cn": 0.169173, "cy": 0.150313, "de": 0.245931, "en": 0.238979, "es": 0.302632, "eu": 0.047486, "fr": 0.247689, "gl": 0.246606, "he": 0.182448, "hi": 0.2, "ir": 0.158763, "kz": 0.025974, "la": 0.154412, "pl": 0.197417, "sl": 0.152475, "uk": 0.225058}, "lang_wp": {"ab": 0.344101, "cn": 0.332707, "cy": 0.275574, "de": 0.443942, "en": 0.406032, "es": 0.538534, "eu": 0.166201, "fr": 0.471349, "gl": 0.421946, "he": 0.382217, "hi": 0.371134, "ir": 0.262887, "kz": 0.145022, "la": 0.378676, "pl": 0.392066, "sl": 0.309901, "uk": 0.445476}, "lang_parsed": {"ab": 0.997191, "cn": 0.99812, "cy": 0.995825, "de": 1.0, "en": 1.0, "es": 0.99812, "eu": 1.0, "fr": 0.998152, "gl": 0.997738, "he": 0.995381, "hi": 0.991753, "ir": 1.0, "kz": 1.0, "la": 0.992647, "pl": 0.994465, "sl": 0.99802, "uk": 1.0}, "lang_mae": {"ab": 1.4479, "cn": 1.7458, "cy": 2.153, "de": 1.3526, "en": 1.3944, "es": 1.0113, "eu": 2.7793, "fr": 1.1426, "gl": 1.3401, "he": 1.3573, "hi": 1.605, "ir": 2.2742, "kz": 2.619, "la": 1.7704, "pl": 1.4026, "sl": 1.8571, "uk": 1.2645}, "confusion": {"1": {"3": 0.349, "4": 0.1004, "1": 0.2542, "2": 0.0675, "6": 0.0328, "5": 0.1961}, "2": {"3": 0.267, "1": 0.2477, "4": 0.1356, "2": 0.0178, "5": 0.3055, "6": 0.0264}, "3": {"3": 0.2143, "4": 0.1555, "5": 0.3973, "1": 0.1964, "6": 0.0298, "2": 0.0067}, "4": {"1": 0.228, "3": 0.1669, "4": 0.1108, "5": 0.4425, "6": 0.0447, "2": 0.0071}, "5": {"3": 0.1017, "5": 0.5232, "4": 0.118, "1": 0.2018, "6": 0.0504, "2": 0.0049}, "6": {"5": 0.5517, "4": 0.0905, "3": 0.0875, "1": 0.1988, "6": 0.0596, "2": 0.0119}}}, {"model": "utter-project/EuroLLM-9B-Instruct-2512", "avg_exact": 0.231279, "avg_wp": 0.366884, "avg_bias": 0.3921, "avg_parsed": 0.99528, "avg_mae": 1.7804, "total": 7839, "lang_exact": {"ab": 0.3, "cn": 0.311808, "cy": 0.171488, "de": 0.145614, "en": 0.200461, "es": 0.340111, "eu": 0.032609, "fr": 0.297101, "gl": 0.192233, "he": 0.251732, "hi": 0.234317, "ir": 0.260194, "kz": 0.088983, "la": 0.503597, "pl": 0.251337, "sl": 0.196154, "uk": 0.21663}, "lang_wp": {"ab": 0.44186, "cn": 0.48155, "cy": 0.320248, "de": 0.229825, "en": 0.357143, "es": 0.487985, "eu": 0.139946, "fr": 0.449275, "gl": 0.317476, "he": 0.39261, "hi": 0.333948, "ir": 0.395146, "kz": 0.305085, "la": 0.589928, "pl": 0.350267, "sl": 0.356731, "uk": 0.364333}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 0.981405, "de": 1.0, "en": 0.997696, "es": 1.0, "eu": 0.986413, "fr": 0.994565, "gl": 1.0, "he": 1.0, "hi": 0.99262, "ir": 0.970874, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.5535, "cn": 1.2177, "cy": 1.8737, "de": 2.5544, "en": 1.6721, "es": 1.2736, "eu": 2.9063, "fr": 1.4536, "gl": 1.9301, "he": 1.6467, "hi": 2.026, "ir": 1.658, "kz": 1.7797, "la": 1.2302, "pl": 1.9501, "sl": 1.6308, "uk": 1.733}, "confusion": {"1": {"3": 0.0755, "1": 0.558, "6": 0.2072, "2": 0.0534, "5": 0.081, "4": 0.0249}, "3": {"1": 0.238, "6": 0.3483, "5": 0.164, "3": 0.188, "2": 0.0348, "4": 0.0269}, "2": {"3": 0.1518, "1": 0.3181, "2": 0.0485, "6": 0.3167, "5": 0.1282, "4": 0.0367}, "4": {"6": 0.4043, "3": 0.1652, "2": 0.0339, "1": 0.2163, "4": 0.0249, "5": 0.1555}, "5": {"6": 0.505, "5": 0.1523, "3": 0.1188, "2": 0.0267, "1": 0.1828, "4": 0.0145}, "6": {"3": 0.0846, "6": 0.5656, "5": 0.1401, "2": 0.0097, "1": 0.1868, "4": 0.0132}}}, {"model": "allenai/Olmo-3-7B-Instruct", "avg_exact": 0.188459, "avg_wp": 0.346885, "avg_bias": 0.4658, "avg_parsed": 0.991082, "avg_mae": 1.6684, "total": 7625, "lang_exact": {"ab": 0.157068, "cn": 0.192453, "cy": 0.177551, "de": 0.158929, "en": 0.281659, "es": 0.231481, "eu": 0.146341, "fr": 0.158182, "gl": 0.146881, "he": 0.186364, "hi": 0.186613, "ir": 0.198381, "kz": 0.208531, "la": 0.178571, "pl": 0.218978, "sl": 0.162745, "uk": 0.210654}, "lang_wp": {"ab": 0.331152, "cn": 0.340566, "cy": 0.331633, "de": 0.298214, "en": 0.451965, "es": 0.397222, "eu": 0.345528, "fr": 0.304545, "gl": 0.274648, "he": 0.364773, "hi": 0.334686, "ir": 0.362348, "kz": 0.327014, "la": 0.271429, "pl": 0.404197, "sl": 0.327451, "uk": 0.376513}, "lang_parsed": {"ab": 0.989529, "cn": 1.0, "cy": 1.0, "de": 0.989286, "en": 0.982533, "es": 0.996296, "eu": 1.0, "fr": 1.0, "gl": 0.981891, "he": 1.0, "hi": 0.933063, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 0.988235, "uk": 1.0}, "lang_mae": {"ab": 1.5714, "cn": 1.8151, "cy": 1.6755, "de": 1.8935, "en": 1.3, "es": 1.4963, "eu": 1.5962, "fr": 1.9036, "gl": 2.0574, "he": 1.5409, "hi": 1.6435, "ir": 1.5243, "kz": 1.5972, "la": 2.2429, "pl": 1.5109, "sl": 1.6448, "uk": 1.5908}, "confusion": {"1": {"3": 0.236, "4": 0.2332, "6": 0.1474, "5": 0.0588, "2": 0.2976, "1": 0.0271}, "2": {"3": 0.2211, "4": 0.233, "6": 0.2091, "5": 0.0575, "2": 0.273, "1": 0.0063}, "3": {"3": 0.1794, "5": 0.0816, "4": 0.2353, "2": 0.2412, "6": 0.261, "1": 0.0015}, "4": {"3": 0.1615, "4": 0.2148, "6": 0.3001, "5": 0.0775, "2": 0.2411, "1": 0.005}, "5": {"6": 0.3787, "3": 0.1346, "4": 0.1886, "2": 0.2224, "5": 0.0709, "1": 0.0048}, "6": {"4": 0.208, "6": 0.3656, "3": 0.1273, "5": 0.0807, "2": 0.207, "1": 0.0114}}}, {"model": "swiss-ai/Apertus-8B-Instruct-2509", "avg_exact": 0.209399, "avg_wp": 0.345723, "avg_bias": -0.0463, "avg_parsed": 0.960564, "avg_mae": 1.7953, "total": 7937, "lang_exact": {"ab": 0.183258, "cn": 0.194805, "cy": 0.17551, "de": 0.221831, "en": 0.28, "es": 0.278598, "eu": 0.132979, "fr": 0.289568, "gl": 0.161793, "he": 0.186139, "hi": 0.190388, "ir": 0.142857, "kz": 0.015625, "la": 0.468531, "pl": 0.258123, "sl": 0.250485, "uk": 0.182222}, "lang_wp": {"ab": 0.279412, "cn": 0.317254, "cy": 0.330612, "de": 0.363556, "en": 0.468889, "es": 0.444649, "eu": 0.295213, "fr": 0.493705, "gl": 0.270955, "he": 0.30099, "hi": 0.278189, "ir": 0.259557, "kz": 0.105469, "la": 0.517483, "pl": 0.364621, "sl": 0.412621, "uk": 0.35}, "lang_parsed": {"ab": 0.963801, "cn": 0.998145, "cy": 0.971429, "de": 0.973592, "en": 0.997778, "es": 0.99262, "eu": 0.989362, "fr": 0.98741, "gl": 0.844055, "he": 0.883168, "hi": 0.992606, "ir": 0.995976, "kz": 0.730469, "la": 0.993007, "pl": 0.998195, "sl": 0.98835, "uk": 0.935556}, "lang_mae": {"ab": 2.2887, "cn": 1.9758, "cy": 1.7815, "de": 1.6799, "en": 1.3229, "es": 1.3736, "eu": 2.0672, "fr": 1.1275, "gl": 1.9215, "he": 1.8296, "hi": 2.3296, "ir": 2.1475, "kz": 2.6898, "la": 1.5775, "pl": 1.8445, "sl": 1.444, "uk": 1.6793}, "confusion": {"1": {"1": 0.479, "6": 0.1789, "3": 0.1817, "4": 0.1025, "2": 0.0391, "5": 0.0186}, "2": {"1": 0.399, "4": 0.0827, "6": 0.2372, "3": 0.1963, "2": 0.0374, "5": 0.0474}, "3": {"1": 0.3447, "4": 0.1127, "6": 0.2454, "3": 0.1913, "5": 0.0808, "2": 0.0252}, "4": {"1": 0.3366, "6": 0.3113, "5": 0.0986, "4": 0.0915, "3": 0.1472, "2": 0.0148}, "5": {"1": 0.2924, "4": 0.0918, "5": 0.1516, "6": 0.3554, "3": 0.0956, "2": 0.0132}, "6": {"1": 0.2443, "6": 0.4643, "5": 0.1665, "3": 0.0643, "2": 0.0072, "4": 0.0534}}}, {"model": "speakleash/Bielik-4.5B-v3.0-Instruct", "avg_exact": 0.180949, "avg_wp": 0.329994, "avg_bias": 0.5962, "avg_parsed": 0.998459, "avg_mae": 1.8388, "total": 6488, "lang_exact": {"ab": 0.106557, "cn": 0.128821, "cy": 0.170213, "de": 0.186312, "en": 0.220513, "es": 0.193294, "eu": 0.119658, "fr": 0.242126, "gl": 0.210773, "he": 0.126154, "hi": 0.172996, "ir": 0.138593, "kz": 0.114035, "la": 0.38806, "pl": 0.270318, "sl": 0.150905, "uk": 0.120755}, "lang_wp": {"ab": 0.241803, "cn": 0.274017, "cy": 0.309574, "de": 0.327947, "en": 0.430769, "es": 0.342209, "eu": 0.316239, "fr": 0.370079, "gl": 0.380562, "he": 0.253846, "hi": 0.305907, "ir": 0.283582, "kz": 0.25, "la": 0.537313, "pl": 0.415194, "sl": 0.299799, "uk": 0.237736}, "lang_parsed": {"ab": 0.995902, "cn": 0.995633, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 0.997658, "he": 0.996923, "hi": 1.0, "ir": 1.0, "kz": 0.991228, "la": 1.0, "pl": 0.9947, "sl": 1.0, "uk": 0.996226}, "lang_mae": {"ab": 2.2346, "cn": 1.9846, "cy": 1.9851, "de": 1.8327, "en": 1.2538, "es": 1.789, "eu": 1.9373, "fr": 1.752, "gl": 1.5235, "he": 2.108, "hi": 2.1097, "ir": 2.0192, "kz": 2.1858, "la": 1.4254, "pl": 1.4813, "sl": 1.9577, "uk": 2.1856}, "confusion": {"1": {"1": 0.3137, "5": 0.6027, "2": 0.0083, "3": 0.0227, "4": 0.0227, "6": 0.0299}, "2": {"1": 0.2562, "5": 0.6172, "4": 0.0652, "3": 0.0357, "2": 0.021, "6": 0.0047}, "3": {"1": 0.1879, "5": 0.6958, "2": 0.0166, "4": 0.0707, "3": 0.0233, "6": 0.0058}, "4": {"1": 0.1923, "5": 0.6846, "4": 0.075, "6": 0.0147, "3": 0.0212, "2": 0.0122}, "5": {"5": 0.6783, "4": 0.0909, "1": 0.1868, "3": 0.028, "6": 0.009, "2": 0.007}, "6": {"5": 0.6063, "1": 0.2114, "4": 0.0975, "3": 0.0215, "2": 0.0076, "6": 0.0557}}}, {"model": "speakleash/Bielik-1.5B-v3.0-Instruct", "avg_exact": 0.145808, "avg_wp": 0.242679, "avg_bias": -1.8483, "avg_parsed": 0.908292, "avg_mae": 2.2702, "total": 6488, "lang_exact": {"ab": 0.217213, "cn": 0.196507, "cy": 0.125532, "de": 0.06654, "en": 0.069231, "es": 0.142012, "eu": 0.017094, "fr": 0.173228, "gl": 0.056206, "he": 0.218462, "hi": 0.223629, "ir": 0.164179, "kz": 0.052632, "la": 0.186567, "pl": 0.233216, "sl": 0.185111, "uk": 0.135849}, "lang_wp": {"ab": 0.331967, "cn": 0.298035, "cy": 0.228723, "de": 0.080798, "en": 0.153846, "es": 0.224852, "eu": 0.131054, "fr": 0.267717, "gl": 0.160422, "he": 0.323077, "hi": 0.333333, "ir": 0.267591, "kz": 0.201754, "la": 0.19403, "pl": 0.366608, "sl": 0.279678, "uk": 0.292453}, "lang_parsed": {"ab": 0.995902, "cn": 0.991266, "cy": 1.0, "de": 0.186312, "en": 0.833333, "es": 0.846154, "eu": 1.0, "fr": 0.992126, "gl": 0.995316, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 0.982332, "sl": 0.995976, "uk": 0.996226}, "lang_mae": {"ab": 2.107, "cn": 2.0595, "cy": 2.4064, "de": 1.8061, "en": 2.3138, "es": 2.3869, "eu": 2.9402, "fr": 2.2599, "gl": 2.6471, "he": 1.9138, "hi": 2.0717, "ir": 2.2345, "kz": 2.4035, "la": 3.3881, "pl": 1.8345, "sl": 2.2505, "uk": 2.0}, "confusion": {"1": {"1": 0.8964, "3": 0.0045, "4": 0.0011, "6": 0.0724, "5": 0.0245, "2": 0.0011}, "2": {"1": 0.916, "2": 0.0009, "6": 0.042, "4": 0.0026, "5": 0.0377, "3": 0.0009}, "3": {"1": 0.8989, "2": 0.0064, "5": 0.0441, "3": 0.0028, "4": 0.0055, "6": 0.0423}, "4": {"1": 0.9007, "2": 0.0027, "6": 0.0537, "5": 0.042, "4": 0.0009}, "5": {"1": 0.8473, "2": 0.0022, "6": 0.0841, "5": 0.0619, "4": 0.0044}, "6": {"1": 0.8203, "6": 0.1114, "5": 0.0641, "2": 0.0028, "3": 0.0014}}}, {"model": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "avg_exact": 0.058268, "avg_wp": 0.098958, "avg_bias": -1.8263, "avg_parsed": 0.371094, "avg_mae": 2.3123, "total": 3072, "lang_exact": {"ab": 0.065909, "cn": 0.059369, "cy": 0.095723, "de": 0.054577, "en": 0.022222, "es": 0.055351, "eu": 0.0}, "lang_wp": {"ab": 0.104545, "cn": 0.093692, "cy": 0.154786, "de": 0.095951, "en": 0.052222, "es": 0.095941, "eu": 0.035714}, "lang_parsed": {"ab": 0.475, "cn": 0.252319, "cy": 0.344196, "de": 0.422535, "en": 0.251111, "es": 0.487085, "eu": 0.214286}, "lang_mae": {"ab": 2.6172, "cn": 1.875, "cy": 1.3432, "de": 2.4917, "en": 2.4779, "es": 2.6818, "eu": 2.3333}, "confusion": {"1": {"1": 0.8014, "6": 0.0355, "5": 0.0426, "2": 0.0567, "4": 0.0355, "3": 0.0284}, "2": {"1": 0.7684, "5": 0.0316, "3": 0.0474, "2": 0.0684, "4": 0.0421, "6": 0.0421}, "3": {"1": 0.7163, "3": 0.0625, "5": 0.0385, "4": 0.0913, "2": 0.0529, "6": 0.0385}, "4": {"1": 0.7512, "6": 0.0861, "5": 0.0335, "3": 0.0239, "4": 0.0813, "2": 0.0239}, "5": {"1": 0.7273, "4": 0.0909, "5": 0.0253, "2": 0.0354, "6": 0.101, "3": 0.0202}, "6": {"1": 0.7474, "4": 0.0825, "2": 0.0361, "5": 0.0361, "6": 0.0928, "3": 0.0052}}}];
|
| 296 |
const ALL_LANGS_2 = ["ab", "eu", "cn", "en", "fr", "gl", "de", "he", "hi", "ir", "kz", "la", "pl", "sl", "es", "uk", "cy"];
|
| 297 |
const LANG_COUNTS_2 = {"ab": 600, "cn": 600, "cy": 560, "de": 600, "en": 521, "es": 600, "eu": 462, "fr": 600, "gl": 520, "he": 600, "hi": 600, "ir": 582, "kz": 328, "la": 189, "pl": 600, "sl": 600, "uk": 530};
|
| 298 |
const LANG_DIST_2 = {"ab": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "cn": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "cy": {"1": 60, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "de": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "en": {"1": 21, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "es": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "eu": {"1": 10, "2": 100, "3": 52, "4": 100, "5": 100, "6": 100}, "fr": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "gl": {"1": 20, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "he": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "hi": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "ir": {"1": 82, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "kz": {"1": 6, "2": 53, "3": 37, "4": 100, "5": 100, "6": 32}, "la": {"1": 34, "2": 3, "3": 3, "4": 35, "5": 14, "6": 100}, "pl": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "sl": {"1": 100, "2": 100, "3": 100, "4": 100, "5": 100, "6": 100}, "uk": {"1": 40, "2": 100, "3": 90, "4": 100, "5": 100, "6": 100}};
|
| 299 |
+
const TOTAL_PREDS_2 = 70374;
|
| 300 |
|
| 301 |
function langName(c) { return LANG_NAMES[c] || c.toUpperCase(); }
|
| 302 |
|
|
|
|
| 318 |
function dsLangs() { return activeDS === 1 ? ALL_LANGS : ALL_LANGS_2; }
|
| 319 |
function dsLangCounts() { return activeDS === 1 ? LANG_COUNTS : LANG_COUNTS_2; }
|
| 320 |
function dsLangDist() { return activeDS === 1 ? LANG_DIST : LANG_DIST_2; }
|
| 321 |
+
function dsTotalPreds() { return activeDS === 1 ? 54333 : TOTAL_PREDS_2; }
|
| 322 |
|
| 323 |
window.setDataset = function(ds) {
|
| 324 |
if (ds === 2 && !HAS_SECOND) return;
|
|
|
|
| 493 |
}).join('');
|
| 494 |
|
| 495 |
document.getElementById('footer').textContent =
|
| 496 |
+
`54333 predictions · ${dsLangs().length} languages · ${dsRows().length} models`;
|
| 497 |
}
|
| 498 |
|
| 499 |
// ── dataset distribution ──
|