adgw commited on
Commit
c2a3de8
·
verified ·
1 Parent(s): 1e8d0af

Update benchmark leaderboard

Browse files
Files changed (1) hide show
  1. index.html +2 -2
index.html CHANGED
@@ -292,11 +292,11 @@
292
 
293
  // second dataset
294
  const HAS_SECOND = true;
295
- const ALL_ROWS_2 = [{"model": "Qwen/Qwen3.5-397B-A17B-FP8", "avg_exact": 0.475149, "avg_wp": 0.66503, "avg_bias": 0.4128, "avg_parsed": 1.0, "avg_mae": 0.7083, "total": 6720, "lang_exact": {"ab": 0.463333, "cn": 0.438333, "cy": 0.332143, "de": 0.551667, "en": 0.587332, "es": 0.57, "eu": 0.38961, "fr": 0.54, "gl": 0.453846, "he": 0.493333, "hi": 0.513333, "ir": 0.31291}, "lang_wp": {"ab": 0.644167, "cn": 0.640833, "cy": 0.528571, "de": 0.725, "en": 0.759117, "es": 0.7425, "eu": 0.574675, "fr": 0.731667, "gl": 0.646154, "he": 0.695, "hi": 0.703333, "ir": 0.539387}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0}, "lang_mae": {"ab": 0.78, "cn": 0.75, "cy": 1.0071, "de": 0.5783, "en": 0.4952, "es": 0.5383, "eu": 0.9351, "fr": 0.5533, "gl": 0.7654, "he": 0.6333, "hi": 0.6133, "ir": 0.9628}, "confusion": {"1": {"1": 0.6697, "2": 0.299, "4": 0.0146, "6": 0.0067, "3": 0.0067, "5": 0.0034}, "2": {"2": 0.515, "4": 0.2225, "3": 0.065, "1": 0.1008, "6": 0.0242, "5": 0.0725}, "3": {"2": 0.2283, "3": 0.0807, "4": 0.4427, "1": 0.013, "6": 0.0356, "5": 0.1997}, "4": {"2": 0.0667, "5": 0.4425, "6": 0.115, "4": 0.3575, "3": 0.0167, "1": 0.0017}, "5": {"6": 0.4409, "4": 0.0979, "5": 0.4366, "2": 0.0213, "3": 0.0034}, "6": {"6": 0.8564, "5": 0.1173, "4": 0.0227, "2": 0.0036}}}, {"model": "mistralai/Mistral-Small-24B-Instruct-2501", "avg_exact": 0.31779, "avg_wp": 0.560195, "avg_bias": 0.0284, "avg_parsed": 1.0, "avg_mae": 0.9057, "total": 7999, "lang_exact": {"ab": 0.294382, "cn": 0.307407, "cy": 0.321932, "de": 0.336824, "en": 0.415755, "es": 0.382353, "eu": 0.289817, "fr": 0.302867, "gl": 0.305609, "he": 0.306641, "hi": 0.241055, "ir": 0.272727, "kz": 0.376923, "la": 0.319444, "pl": 0.341727, "sl": 0.295585, "uk": 0.318681}, "lang_wp": {"ab": 0.529213, "cn": 0.544444, "cy": 0.560362, "de": 0.576789, "en": 0.671772, "es": 0.639706, "eu": 0.523499, "fr": 0.580645, "gl": 0.56383, "he": 0.544922, "hi": 0.461394, "ir": 0.513834, "kz": 0.621154, "la": 0.402778, "pl": 0.570144, "sl": 0.536468, "uk": 0.596703}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 0.9843, "cn": 0.963, "cy": 0.8954, "de": 0.8709, "en": 0.6718, "es": 0.7243, "eu": 0.9687, "fr": 0.8548, "gl": 0.8878, "he": 0.9414, "hi": 1.1337, "ir": 1.0099, "kz": 0.7577, "la": 1.3056, "pl": 0.8759, "sl": 0.9539, "uk": 0.8154}, "confusion": {"3": {"4": 0.5322, "2": 0.0946, "3": 0.346, "1": 0.01, "6": 0.0007, "5": 0.0165}, "2": {"4": 0.3167, "2": 0.2579, "3": 0.4001, "1": 0.0219, "5": 0.0034}, "1": {"2": 0.4823, "3": 0.2102, "1": 0.2138, "4": 0.0919, "6": 0.0018}, "4": {"4": 0.6669, "3": 0.2057, "2": 0.0512, "5": 0.0708, "1": 0.0054}, "5": {"4": 0.5988, "5": 0.3031, "3": 0.0791, "2": 0.0132, "6": 0.0059}, "6": {"4": 0.399, "5": 0.5197, "3": 0.0335, "6": 0.0369, "2": 0.0075, "1": 0.0034}}}, {"model": "allenai/Olmo-3.1-32B-Instruct", "avg_exact": 0.35418, "avg_wp": 0.549877, "avg_bias": 0.6144, "avg_parsed": 1.0, "avg_mae": 1.0553, "total": 7739, "lang_exact": {"ab": 0.355499, "cn": 0.368715, "cy": 0.346154, "de": 0.37766, "en": 0.369892, "es": 0.468635, "eu": 0.312668, "fr": 0.4, "gl": 0.321569, "he": 0.281319, "hi": 0.357853, "ir": 0.348606, "kz": 0.164444, "la": 0.464789, "pl": 0.388385, "sl": 0.327485, "uk": 0.295943}, "lang_wp": {"ab": 0.528133, "cn": 0.566108, "cy": 0.552632, "de": 0.575355, "en": 0.563441, "es": 0.664207, "eu": 0.494609, "fr": 0.597297, "gl": 0.52549, "he": 0.497802, "hi": 0.549702, "ir": 0.557769, "kz": 0.386667, "la": 0.489437, "pl": 0.595281, "sl": 0.515595, "uk": 0.502387}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.202, "cn": 0.9777, "cy": 1.0223, "de": 1.0018, "en": 1.0817, "es": 0.7583, "eu": 1.1968, "fr": 0.9099, "gl": 1.1, "he": 1.1231, "hi": 1.0676, "ir": 0.9622, "kz": 1.44, "la": 1.8592, "pl": 0.9274, "sl": 1.1384, "uk": 1.1074}, "confusion": {"1": {"1": 0.5078, "6": 0.0683, "3": 0.1588, "2": 0.2133, "5": 0.0185, "4": 0.0332}, "2": {"1": 0.1237, "3": 0.3462, "4": 0.1493, "5": 0.0891, "2": 0.1465, "6": 0.1451}, "3": {"1": 0.0211, "2": 0.0605, "6": 0.1355, "3": 0.3336, "4": 0.2658, "5": 0.1835}, "4": {"5": 0.2575, "3": 0.2026, "4": 0.2484, "6": 0.2498, "2": 0.0236, "1": 0.018}, "5": {"4": 0.1315, "6": 0.5058, "5": 0.2848, "3": 0.0623, "1": 0.0086, "2": 0.007}, "6": {"6": 0.718, "5": 0.1694, "4": 0.0613, "3": 0.027, "2": 0.0009, "1": 0.0234}}}, {"model": "speakleash/Bielik-11B-v3.0-Instruct", "avg_exact": 0.319321, "avg_wp": 0.52795, "avg_bias": -0.0152, "avg_parsed": 0.967946, "avg_mae": 1.0378, "total": 9016, "lang_exact": {"ab": 0.263525, "cn": 0.406518, "cy": 0.264286, "de": 0.366667, "en": 0.341651, "es": 0.446667, "eu": 0.244589, "fr": 0.433333, "gl": 0.290385, "he": 0.22031, "hi": 0.282794, "ir": 0.333333, "kz": 0.335366, "la": 0.243386, "pl": 0.193333, "sl": 0.311667, "uk": 0.388679}, "lang_wp": {"ab": 0.426702, "cn": 0.626072, "cy": 0.502679, "de": 0.595, "en": 0.587332, "es": 0.6625, "eu": 0.462121, "fr": 0.665, "gl": 0.524038, "he": 0.36747, "hi": 0.459114, "ir": 0.542955, "kz": 0.573171, "la": 0.402116, "pl": 0.3625, "sl": 0.524167, "uk": 0.619811}, "lang_parsed": {"ab": 0.900524, "cn": 0.96741, "cy": 1.0, "de": 0.996667, "en": 0.994242, "es": 0.995, "eu": 0.980519, "fr": 1.0, "gl": 1.0, "he": 0.977625, "hi": 0.938671, "ir": 0.998282, "kz": 0.990854, "la": 0.994709, "pl": 0.903333, "sl": 0.933333, "uk": 0.916981}, "lang_mae": {"ab": 1.2868, "cn": 0.7695, "cy": 1.0911, "de": 0.8645, "en": 0.8842, "es": 0.6851, "eu": 1.2075, "fr": 0.6867, "gl": 1.0038, "he": 1.5933, "hi": 1.1887, "ir": 0.9725, "kz": 0.9046, "la": 2.0904, "pl": 1.4963, "sl": 0.9571, "uk": 0.6667}, "confusion": {"1": {"1": 0.748, "5": 0.0537, "2": 0.0661, "6": 0.0018, "4": 0.096, "3": 0.0344}, "2": {"2": 0.1071, "1": 0.2756, "3": 0.1783, "5": 0.128, "4": 0.3109}, "3": {"1": 0.1199, "4": 0.4262, "5": 0.2148, "3": 0.1816, "2": 0.0575}, "4": {"1": 0.0789, "4": 0.3598, "5": 0.428, "3": 0.1086, "2": 0.024, "6": 0.0006}, "5": {"3": 0.0566, "4": 0.2227, "1": 0.0436, "5": 0.6719, "2": 0.0052}, "6": {"5": 0.7356, "1": 0.0781, "3": 0.0374, "4": 0.1422, "2": 0.0053, "6": 0.0013}}}, {"model": "Qwen/Qwen2.5-14B-Instruct", "avg_exact": 0.278385, "avg_wp": 0.516447, "avg_bias": 0.053, "avg_parsed": 1.0, "avg_mae": 0.9821, "total": 7874, "lang_exact": {"ab": 0.253968, "cn": 0.291367, "cy": 0.308316, "de": 0.278571, "en": 0.324561, "es": 0.305556, "eu": 0.248649, "fr": 0.337545, "gl": 0.252964, "he": 0.276062, "hi": 0.226824, "ir": 0.282869, "kz": 0.341772, "la": 0.262411, "pl": 0.21558, "sl": 0.268627, "uk": 0.269142}, "lang_wp": {"ab": 0.503401, "cn": 0.555755, "cy": 0.548682, "de": 0.5125, "en": 0.569079, "es": 0.557407, "eu": 0.467568, "fr": 0.563177, "gl": 0.499012, "he": 0.52027, "hi": 0.455621, "ir": 0.513944, "kz": 0.586498, "la": 0.358156, "pl": 0.447464, "sl": 0.510784, "uk": 0.520882}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.0113, "cn": 0.8903, "cy": 0.9148, "de": 0.9839, "en": 0.8684, "es": 0.8889, "eu": 1.0973, "fr": 0.8809, "gl": 1.0158, "he": 0.9807, "hi": 1.1144, "ir": 1.0, "kz": 0.827, "la": 1.3333, "pl": 1.125, "sl": 1.0039, "uk": 0.9606}, "confusion": {"1": {"1": 0.1435, "2": 0.4625, "3": 0.3373, "4": 0.0567}, "2": {"3": 0.4684, "2": 0.1699, "4": 0.3432, "1": 0.011, "5": 0.0076}, "3": {"4": 0.5922, "2": 0.049, "3": 0.3429, "5": 0.0144, "1": 0.0007, "6": 0.0007}, "4": {"4": 0.7609, "3": 0.1776, "5": 0.043, "2": 0.0178, "6": 0.0007}, "5": {"4": 0.8014, "5": 0.143, "3": 0.0504, "2": 0.003, "6": 0.0023}, "6": {"5": 0.2314, "4": 0.7293, "6": 0.007, "3": 0.0297, "2": 0.0026}}}, {"model": "utter-project/EuroLLM-22B-Instruct-2512", "avg_exact": 0.298877, "avg_wp": 0.513694, "avg_bias": 0.574, "avg_parsed": 0.999874, "avg_mae": 1.1195, "total": 7923, "lang_exact": {"ab": 0.361751, "cn": 0.33945, "cy": 0.254582, "de": 0.326353, "en": 0.253363, "es": 0.368324, "eu": 0.22372, "fr": 0.389892, "gl": 0.294004, "he": 0.257778, "hi": 0.302026, "ir": 0.351248, "kz": 0.293878, "la": 0.194444, "pl": 0.216696, "sl": 0.272553, "uk": 0.266234}, "lang_wp": {"ab": 0.570276, "cn": 0.569725, "cy": 0.482688, "de": 0.546248, "en": 0.439462, "es": 0.581952, "eu": 0.443396, "fr": 0.591155, "gl": 0.525145, "he": 0.444444, "hi": 0.524862, "ir": 0.56238, "kz": 0.504082, "la": 0.524306, "pl": 0.409414, "sl": 0.482726, "uk": 0.492424}, "lang_parsed": {"ab": 1.0, "cn": 0.998165, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 0.9401, "cn": 0.9154, "cy": 1.1527, "de": 1.0489, "en": 1.3161, "es": 0.9134, "eu": 1.3477, "fr": 0.9206, "gl": 1.0387, "he": 1.3711, "hi": 1.0829, "ir": 0.9712, "kz": 1.1796, "la": 1.2083, "pl": 1.4938, "sl": 1.2054, "uk": 1.132}, "confusion": {"2": {"1": 0.068, "5": 0.455, "2": 0.3491, "4": 0.0034, "3": 0.1203, "6": 0.0041}, "1": {"1": 0.3846, "2": 0.4139, "5": 0.1465, "3": 0.0513, "6": 0.0037}, "3": {"5": 0.7158, "2": 0.1568, "1": 0.018, "3": 0.1065, "6": 0.0022, "4": 0.0007}, "4": {"5": 0.8645, "2": 0.0735, "3": 0.049, "4": 0.0027, "6": 0.0027, "1": 0.0075}, "5": {"5": 0.936, "2": 0.0387, "3": 0.0097, "6": 0.0082, "1": 0.0045, "4": 0.003}, "6": {"5": 0.9403, "1": 0.0094, "6": 0.0256, "2": 0.0179, "4": 0.0017, "3": 0.0051}}}, {"model": "CYFRAGOVPL/Llama-PLLuM-70B-chat-250801", "avg_exact": 0.275562, "avg_wp": 0.474108, "avg_bias": -0.6122, "avg_parsed": 0.996364, "avg_mae": 1.2257, "total": 9076, "lang_exact": {"ab": 0.297479, "cn": 0.248333, "cy": 0.276786, "de": 0.363333, "en": 0.243762, "es": 0.295, "eu": 0.166667, "fr": 0.318333, "gl": 0.201923, "he": 0.243655, "hi": 0.281667, "ir": 0.262887, "kz": 0.303681, "la": 0.216931, "pl": 0.316667, "sl": 0.331667, "uk": 0.245283}, "lang_wp": {"ab": 0.485714, "cn": 0.39, "cy": 0.504464, "de": 0.561667, "en": 0.487524, "es": 0.491667, "eu": 0.376623, "fr": 0.511667, "gl": 0.414423, "he": 0.423012, "hi": 0.471667, "ir": 0.444158, "kz": 0.546012, "la": 0.304233, "pl": 0.520833, "sl": 0.5425, "uk": 0.471698}, "lang_parsed": {"ab": 0.986555, "cn": 1.0, "cy": 0.998214, "de": 1.0, "en": 0.992322, "es": 0.996667, "eu": 0.997835, "fr": 0.998333, "gl": 1.0, "he": 0.99154, "hi": 1.0, "ir": 0.994845, "kz": 0.996933, "la": 1.0, "pl": 0.993333, "sl": 0.996667, "uk": 0.998113}, "lang_mae": {"ab": 1.1806, "cn": 1.5733, "cy": 1.102, "de": 1.0117, "en": 1.1277, "es": 1.1488, "eu": 1.4967, "fr": 1.1002, "gl": 1.3058, "he": 1.3379, "hi": 1.2433, "ir": 1.3368, "kz": 1.0092, "la": 2.3439, "pl": 1.0419, "sl": 0.9916, "uk": 1.2042}, "confusion": {"1": {"3": 0.1541, "1": 0.786, "4": 0.0317, "5": 0.0154, "6": 0.0051, "2": 0.0077}, "2": {"3": 0.3323, "4": 0.1092, "1": 0.4874, "5": 0.0595, "2": 0.0071, "6": 0.0045}, "3": {"1": 0.3083, "3": 0.3807, "5": 0.1244, "4": 0.1765, "2": 0.0054, "6": 0.0047}, "4": {"4": 0.2148, "3": 0.3557, "5": 0.216, "1": 0.2037, "6": 0.0055, "2": 0.0043}, "5": {"5": 0.3859, "4": 0.2643, "3": 0.2506, "1": 0.0842, "2": 0.0044, "6": 0.0106}, "6": {"4": 0.2679, "3": 0.1772, "5": 0.4247, "1": 0.1019, "6": 0.0253, "2": 0.0031}}}, {"model": "mistralai/Mistral-Nemo-Instruct-2407", "avg_exact": 0.282611, "avg_wp": 0.468668, "avg_bias": -0.2413, "avg_parsed": 0.963425, "avg_mae": 1.2449, "total": 8011, "lang_exact": {"ab": 0.29148, "cn": 0.3, "cy": 0.181087, "de": 0.279232, "en": 0.323851, "es": 0.310662, "eu": 0.263708, "fr": 0.351254, "gl": 0.257253, "he": 0.289062, "hi": 0.265683, "ir": 0.243083, "kz": 0.296154, "la": 0.180556, "pl": 0.354317, "sl": 0.28215, "uk": 0.248352}, "lang_wp": {"ab": 0.483184, "cn": 0.492593, "cy": 0.343058, "de": 0.507853, "en": 0.507659, "es": 0.511949, "eu": 0.425587, "fr": 0.562724, "gl": 0.434236, "he": 0.487305, "hi": 0.417897, "ir": 0.380435, "kz": 0.457692, "la": 0.322917, "pl": 0.546763, "sl": 0.478887, "uk": 0.465934}, "lang_parsed": {"ab": 0.950673, "cn": 0.983333, "cy": 0.987928, "de": 0.95637, "en": 0.964989, "es": 0.977941, "eu": 0.942559, "fr": 0.958781, "gl": 0.912959, "he": 0.988281, "hi": 0.968635, "ir": 0.966403, "kz": 0.915385, "la": 0.9375, "pl": 0.992806, "sl": 0.955854, "uk": 0.967033}, "lang_mae": {"ab": 1.1085, "cn": 1.2298, "cy": 1.8045, "de": 1.042, "en": 1.0, "es": 1.1015, "eu": 1.3989, "fr": 0.8991, "gl": 1.2712, "he": 1.1739, "hi": 1.499, "ir": 1.5808, "kz": 1.1723, "la": 2.2148, "pl": 1.0145, "sl": 1.2129, "uk": 1.1795}, "confusion": {"1": {"1": 0.4749, "2": 0.3597, "5": 0.0799, "4": 0.0288, "3": 0.0483, "6": 0.0084}, "2": {"4": 0.1264, "2": 0.4316, "5": 0.176, "1": 0.1669, "3": 0.0866, "6": 0.0126}, "3": {"4": 0.2181, "1": 0.0934, "2": 0.3071, "3": 0.1225, "5": 0.248, "6": 0.0109}, "4": {"4": 0.2169, "2": 0.2479, "5": 0.3336, "1": 0.076, "3": 0.1105, "6": 0.0152}, "5": {"4": 0.1957, "2": 0.1995, "5": 0.4612, "1": 0.0491, "6": 0.0269, "3": 0.0675}, "6": {"5": 0.5312, "4": 0.1379, "2": 0.1544, "6": 0.0478, "1": 0.08, "3": 0.0487}}}, {"model": "Qwen/Qwen2.5-7B-Instruct", "avg_exact": 0.285497, "avg_wp": 0.461773, "avg_bias": 0.9564, "avg_parsed": 1.0, "avg_mae": 1.212, "total": 7874, "lang_exact": {"ab": 0.283447, "cn": 0.305755, "cy": 0.219067, "de": 0.341071, "en": 0.296053, "es": 0.362963, "eu": 0.267568, "fr": 0.370036, "gl": 0.304348, "he": 0.272201, "hi": 0.258383, "ir": 0.213147, "kz": 0.278481, "la": 0.35461, "pl": 0.286232, "sl": 0.190196, "uk": 0.266821}, "lang_wp": {"ab": 0.451247, "cn": 0.48741, "cy": 0.408722, "de": 0.525893, "en": 0.501096, "es": 0.531481, "eu": 0.422973, "fr": 0.546029, "gl": 0.503953, "he": 0.44305, "hi": 0.431953, "ir": 0.376494, "kz": 0.440928, "la": 0.574468, "pl": 0.429348, "sl": 0.347059, "uk": 0.472158}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.3107, "cn": 1.1259, "cy": 1.3266, "de": 1.0429, "en": 1.0658, "es": 1.0093, "eu": 1.3081, "fr": 0.9585, "gl": 1.0514, "he": 1.2838, "hi": 1.284, "ir": 1.4422, "kz": 1.1772, "la": 1.0, "pl": 1.4094, "sl": 1.5529, "uk": 1.1439}, "confusion": {"1": {"1": 0.3062, "3": 0.2678, "4": 0.3291, "6": 0.0283, "2": 0.0375, "5": 0.0311}, "2": {"2": 0.0186, "3": 0.1403, "4": 0.6272, "5": 0.1039, "1": 0.0413, "6": 0.0688}, "3": {"4": 0.611, "6": 0.1318, "2": 0.0029, "5": 0.2089, "3": 0.0389, "1": 0.0065}, "4": {"6": 0.2281, "4": 0.4597, "5": 0.2937, "3": 0.0143, "1": 0.0041}, "5": {"6": 0.4387, "4": 0.2092, "5": 0.3506, "3": 0.0015}, "6": {"6": 0.6052, "4": 0.1231, "5": 0.2681, "3": 0.0026, "1": 0.0009}}}, {"model": "speakleash/Bielik-11B-v2.6-Instruct", "avg_exact": 0.261933, "avg_wp": 0.461439, "avg_bias": 0.4995, "avg_parsed": 1.0, "avg_mae": 1.2414, "total": 8506, "lang_exact": {"ab": 0.214533, "cn": 0.250432, "cy": 0.219031, "de": 0.268456, "en": 0.321705, "es": 0.361204, "eu": 0.197397, "fr": 0.301667, "gl": 0.280769, "he": 0.238384, "hi": 0.23689, "ir": 0.183849, "kz": 0.206642, "la": 0.196721, "pl": 0.321667, "sl": 0.26, "uk": 0.280632}, "lang_wp": {"ab": 0.378893, "cn": 0.42228, "cy": 0.40754, "de": 0.466443, "en": 0.543605, "es": 0.574415, "eu": 0.439262, "fr": 0.526667, "gl": 0.523077, "he": 0.437374, "hi": 0.391501, "ir": 0.354811, "kz": 0.47417, "la": 0.289617, "pl": 0.498333, "sl": 0.438333, "uk": 0.530632}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.4948, "cn": 1.361, "cy": 1.3429, "de": 1.203, "en": 1.0039, "es": 0.903, "eu": 1.282, "fr": 0.9917, "gl": 1.0442, "he": 1.1636, "hi": 1.5461, "ir": 1.5155, "kz": 1.0701, "la": 1.9563, "pl": 1.315, "sl": 1.375, "uk": 1.0119}, "confusion": {"1": {"3": 0.653, "1": 0.2373, "6": 0.0874, "5": 0.0223}, "2": {"3": 0.7263, "5": 0.1183, "6": 0.1079, "1": 0.0195, "4": 0.028}, "3": {"3": 0.5543, "6": 0.1349, "5": 0.2886, "4": 0.0201, "1": 0.0021}, "4": {"3": 0.4415, "6": 0.1742, "5": 0.3612, "4": 0.0219, "1": 0.0013}, "6": {"3": 0.2302, "6": 0.3566, "5": 0.4009, "4": 0.0065, "1": 0.0058}, "5": {"5": 0.4329, "3": 0.2825, "6": 0.2621, "4": 0.0218, "2": 0.0007}}}, {"model": "allenai/Olmo-3-7B-Instruct", "avg_exact": 0.228195, "avg_wp": 0.409937, "avg_bias": 0.5317, "avg_parsed": 0.999612, "avg_mae": 1.4272, "total": 7739, "lang_exact": {"ab": 0.176471, "cn": 0.214153, "cy": 0.204453, "de": 0.23227, "en": 0.292473, "es": 0.287823, "eu": 0.221024, "fr": 0.23964, "gl": 0.264706, "he": 0.178022, "hi": 0.252485, "ir": 0.181275, "kz": 0.213333, "la": 0.211268, "pl": 0.257713, "sl": 0.163743, "uk": 0.250597}, "lang_wp": {"ab": 0.391304, "cn": 0.368715, "cy": 0.385628, "de": 0.437943, "en": 0.489247, "es": 0.511993, "eu": 0.392183, "fr": 0.423423, "gl": 0.431373, "he": 0.36044, "hi": 0.437376, "ir": 0.35757, "kz": 0.397778, "la": 0.31338, "pl": 0.434664, "sl": 0.309942, "uk": 0.435561}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 0.998227, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 0.998012, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 0.998185, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.3632, "cn": 1.5736, "cy": 1.4555, "de": 1.3091, "en": 1.1634, "es": 1.0996, "eu": 1.5553, "fr": 1.3892, "gl": 1.4078, "he": 1.5231, "hi": 1.3625, "ir": 1.498, "kz": 1.3911, "la": 1.7042, "pl": 1.4691, "sl": 1.8226, "uk": 1.3771}, "confusion": {"1": {"3": 0.2114, "4": 0.157, "2": 0.4035, "1": 0.0905, "5": 0.0766, "6": 0.0609}, "2": {"1": 0.027, "3": 0.1728, "4": 0.2122, "5": 0.1638, "6": 0.114, "2": 0.3103}, "3": {"3": 0.1151, "2": 0.2367, "4": 0.2251, "6": 0.1653, "5": 0.2535, "1": 0.0044}, "4": {"4": 0.1985, "3": 0.0985, "6": 0.2415, "2": 0.186, "5": 0.2741, "1": 0.0014}, "5": {"4": 0.1877, "6": 0.3879, "3": 0.0724, "5": 0.2033, "2": 0.148, "1": 0.0008}, "6": {"6": 0.4639, "5": 0.1597, "4": 0.1634, "3": 0.0731, "2": 0.139, "1": 0.0009}}}, {"model": "mistralai/Mistral-7B-Instruct-v0.3", "avg_exact": 0.229035, "avg_wp": 0.398141, "avg_bias": 0.9606, "avg_parsed": 0.994066, "avg_mae": 1.5188, "total": 7584, "lang_exact": {"ab": 0.224599, "cn": 0.208566, "cy": 0.220619, "de": 0.253142, "en": 0.16895, "es": 0.36194, "eu": 0.208914, "fr": 0.261993, "gl": 0.208791, "he": 0.199557, "hi": 0.240481, "ir": 0.197154, "kz": 0.228814, "la": 0.154412, "pl": 0.259191, "sl": 0.182711, "uk": 0.223502}, "lang_wp": {"ab": 0.415775, "cn": 0.388268, "cy": 0.371134, "de": 0.435368, "en": 0.326484, "es": 0.539179, "eu": 0.410864, "fr": 0.445572, "gl": 0.369231, "he": 0.379157, "hi": 0.403808, "ir": 0.327236, "kz": 0.427966, "la": 0.386029, "pl": 0.409007, "sl": 0.319253, "uk": 0.396313}, "lang_parsed": {"ab": 0.994652, "cn": 0.998138, "cy": 0.995876, "de": 0.994614, "en": 0.993151, "es": 0.994403, "eu": 0.997214, "fr": 0.99262, "gl": 0.997802, "he": 0.997783, "hi": 0.98998, "ir": 0.989837, "kz": 0.970339, "la": 0.977941, "pl": 1.0, "sl": 0.996071, "uk": 0.995392}, "lang_mae": {"ab": 1.371, "cn": 1.4981, "cy": 1.6418, "de": 1.37, "en": 1.7586, "es": 1.1032, "eu": 1.486, "fr": 1.3309, "gl": 1.5991, "he": 1.4422, "hi": 1.5668, "ir": 1.8029, "kz": 1.31, "la": 1.6692, "pl": 1.5625, "sl": 1.8679, "uk": 1.4769}, "confusion": {"2": {"4": 0.0677, "5": 0.3656, "1": 0.1214, "3": 0.2357, "2": 0.0247, "6": 0.1849}, "1": {"3": 0.2608, "1": 0.3499, "2": 0.0582, "5": 0.1839, "6": 0.1126, "4": 0.0347}, "4": {"3": 0.1364, "5": 0.4961, "4": 0.0473, "6": 0.2608, "1": 0.0382, "2": 0.0212}, "5": {"5": 0.5188, "2": 0.016, "3": 0.0721, "6": 0.3443, "4": 0.0328, "1": 0.016}, "3": {"5": 0.4767, "4": 0.0665, "3": 0.1663, "2": 0.0237, "6": 0.2106, "1": 0.0562}, "6": {"5": 0.4899, "4": 0.0308, "3": 0.0645, "6": 0.3744, "2": 0.0115, "1": 0.0289}}}, {"model": "cjvt/GaMS3-12B-Instruct", "avg_exact": 0.223201, "avg_wp": 0.38902, "avg_bias": 0.7368, "avg_parsed": 0.999876, "avg_mae": 1.4632, "total": 8060, "lang_exact": {"ab": 0.301339, "cn": 0.212613, "cy": 0.157258, "de": 0.217014, "en": 0.235931, "es": 0.210238, "eu": 0.18254, "fr": 0.183124, "gl": 0.223938, "he": 0.25, "hi": 0.268116, "ir": 0.200393, "kz": 0.155894, "la": 0.536913, "pl": 0.2375, "sl": 0.193858, "uk": 0.21692}, "lang_wp": {"ab": 0.459821, "cn": 0.364865, "cy": 0.336694, "de": 0.378472, "en": 0.452381, "es": 0.390311, "eu": 0.371693, "fr": 0.35368, "gl": 0.399614, "he": 0.436024, "hi": 0.424819, "ir": 0.311395, "kz": 0.368821, "la": 0.583893, "pl": 0.372321, "sl": 0.350288, "uk": 0.402386}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 0.997831}, "lang_mae": {"ab": 1.2612, "cn": 1.5964, "cy": 1.5323, "de": 1.5556, "en": 1.1645, "es": 1.3346, "eu": 1.4603, "fr": 1.4237, "gl": 1.444, "he": 1.2559, "hi": 1.3967, "ir": 1.8468, "kz": 1.4335, "la": 1.255, "pl": 1.7446, "sl": 1.5566, "uk": 1.3543}, "confusion": {"2": {"4": 0.3051, "1": 0.0567, "5": 0.2137, "3": 0.2594, "6": 0.1563, "2": 0.0089}, "3": {"4": 0.269, "5": 0.3915, "6": 0.1516, "3": 0.1715, "1": 0.0114, "2": 0.005}, "1": {"1": 0.3159, "6": 0.1182, "4": 0.1336, "3": 0.3655, "5": 0.0379, "2": 0.0289}, "4": {"4": 0.2047, "6": 0.1785, "3": 0.1604, "5": 0.4396, "1": 0.0114, "2": 0.0054}, "5": {"5": 0.3671, "4": 0.2143, "6": 0.2339, "3": 0.1752, "1": 0.0072, "2": 0.0022}, "6": {"6": 0.3165, "5": 0.2314, "4": 0.243, "3": 0.1901, "1": 0.0165, "2": 0.0025}}}, {"model": "swiss-ai/Apertus-8B-Instruct-2509", "avg_exact": 0.226841, "avg_wp": 0.368914, "avg_bias": 1.3785, "avg_parsed": 0.989763, "avg_mae": 1.7385, "total": 8010, "lang_exact": {"ab": 0.238202, "cn": 0.22037, "cy": 0.205231, "de": 0.247818, "en": 0.207877, "es": 0.277574, "eu": 0.224543, "fr": 0.340502, "gl": 0.224371, "he": 0.132812, "hi": 0.208487, "ir": 0.20751, "kz": 0.165385, "la": 0.506944, "pl": 0.223022, "sl": 0.197697, "uk": 0.178022}, "lang_wp": {"ab": 0.347191, "cn": 0.387963, "cy": 0.325956, "de": 0.410122, "en": 0.364333, "es": 0.418199, "eu": 0.390339, "fr": 0.537634, "gl": 0.341393, "he": 0.24707, "hi": 0.353321, "ir": 0.368577, "kz": 0.35, "la": 0.548611, "pl": 0.317446, "sl": 0.330134, "uk": 0.331868}, "lang_parsed": {"ab": 0.966292, "cn": 0.998148, "cy": 0.993964, "de": 1.0, "en": 1.0, "es": 0.996324, "eu": 0.986945, "fr": 0.996416, "gl": 0.996132, "he": 0.986328, "hi": 0.990775, "ir": 0.998024, "kz": 0.903846, "la": 0.972222, "pl": 0.998201, "sl": 0.996161, "uk": 0.984615}, "lang_mae": {"ab": 1.8721, "cn": 1.5158, "cy": 1.913, "de": 1.5445, "en": 1.6893, "es": 1.4668, "eu": 1.6323, "fr": 1.0917, "gl": 1.8699, "he": 2.2693, "hi": 1.8994, "ir": 1.7446, "kz": 1.4723, "la": 1.3929, "pl": 2.1369, "sl": 1.8825, "uk": 1.8438}, "confusion": {"2": {"6": 0.5169, "3": 0.1884, "1": 0.0856, "2": 0.1304, "5": 0.0649, "4": 0.0138}, "1": {"6": 0.3163, "3": 0.2203, "1": 0.2477, "4": 0.0165, "5": 0.0238, "2": 0.1755}, "3": {"6": 0.6273, "3": 0.1288, "1": 0.0317, "2": 0.0791, "4": 0.0187, "5": 0.1144}, "4": {"6": 0.6785, "5": 0.1539, "3": 0.0828, "1": 0.0321, "4": 0.0178, "2": 0.0349}, "5": {"5": 0.1532, "6": 0.7654, "3": 0.0244, "1": 0.0222, "2": 0.0185, "4": 0.0163}, "6": {"6": 0.7995, "5": 0.1261, "2": 0.0068, "4": 0.0161, "3": 0.0279, "1": 0.0237}}}, {"model": "speakleash/Bielik-1.5B-v3.0-Instruct", "avg_exact": 0.206902, "avg_wp": 0.363133, "avg_bias": -0.3521, "avg_parsed": 0.999854, "avg_mae": 1.7134, "total": 6868, "lang_exact": {"ab": 0.178694, "cn": 0.230932, "cy": 0.164927, "de": 0.225746, "en": 0.265306, "es": 0.238921, "eu": 0.143258, "fr": 0.210832, "gl": 0.229167, "he": 0.174263, "hi": 0.178082, "ir": 0.164241, "kz": 0.114094, "la": 0.126866, "pl": 0.268078, "sl": 0.268537, "uk": 0.143791}, "lang_wp": {"ab": 0.302405, "cn": 0.377119, "cy": 0.317328, "de": 0.403918, "en": 0.452806, "es": 0.416185, "eu": 0.296348, "fr": 0.404255, "gl": 0.436343, "he": 0.323056, "hi": 0.286301, "ir": 0.277547, "kz": 0.288591, "la": 0.164179, "pl": 0.417989, "sl": 0.428858, "uk": 0.289216}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 0.997449, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 2.1512, "cn": 1.6589, "cy": 1.9019, "de": 1.5392, "en": 1.2506, "es": 1.4644, "eu": 2.014, "fr": 1.4255, "gl": 1.1968, "he": 1.8365, "hi": 2.2658, "ir": 2.1497, "kz": 2.0738, "la": 2.6493, "pl": 1.5185, "sl": 1.4469, "uk": 1.9869}, "confusion": {"1": {"1": 0.5015, "5": 0.2251, "6": 0.0336, "2": 0.0809, "4": 0.1333, "3": 0.0257}, "2": {"1": 0.4241, "5": 0.1975, "4": 0.2221, "2": 0.1047, "6": 0.0269, "3": 0.0247}, "3": {"1": 0.3597, "2": 0.0854, "5": 0.2182, "4": 0.2877, "3": 0.0253, "6": 0.0237}, "4": {"1": 0.3423, "5": 0.2571, "6": 0.0384, "4": 0.2678, "2": 0.0806, "3": 0.0138}, "5": {"1": 0.2749, "5": 0.3123, "6": 0.0447, "4": 0.2603, "2": 0.0868, "3": 0.021}, "6": {"1": 0.2752, "5": 0.3571, "2": 0.0539, "6": 0.0585, "4": 0.2307, "3": 0.0246}}}, {"model": "speakleash/Bielik-4.5B-v3.0-Instruct", "avg_exact": 0.188847, "avg_wp": 0.338818, "avg_bias": 1.1003, "avg_parsed": 1.0, "avg_mae": 1.7567, "total": 6868, "lang_exact": {"ab": 0.154639, "cn": 0.152542, "cy": 0.17119, "de": 0.169776, "en": 0.191327, "es": 0.22158, "eu": 0.129213, "fr": 0.193424, "gl": 0.196759, "he": 0.201072, "hi": 0.191781, "ir": 0.2079, "kz": 0.255034, "la": 0.462687, "pl": 0.17284, "sl": 0.162325, "uk": 0.202614}, "lang_wp": {"ab": 0.286942, "cn": 0.313559, "cy": 0.331942, "de": 0.29291, "en": 0.359694, "es": 0.32948, "eu": 0.29073, "fr": 0.330754, "gl": 0.359954, "he": 0.348525, "hi": 0.349315, "ir": 0.373181, "kz": 0.489933, "la": 0.55597, "pl": 0.324515, "sl": 0.313627, "uk": 0.367647}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.8007, "cn": 1.786, "cy": 1.739, "de": 1.9888, "en": 1.5357, "es": 1.9094, "eu": 2.0674, "fr": 1.7988, "gl": 1.5995, "he": 1.6756, "hi": 1.7342, "ir": 1.5738, "kz": 1.1812, "la": 1.2015, "pl": 1.8554, "sl": 1.8858, "uk": 1.6471}, "confusion": {"2": {"4": 0.1429, "5": 0.6133, "1": 0.101, "3": 0.0868, "6": 0.0561}, "3": {"5": 0.6411, "4": 0.1186, "1": 0.0822, "6": 0.0909, "3": 0.0672}, "1": {"1": 0.1598, "4": 0.1696, "5": 0.5276, "3": 0.1016, "6": 0.0414}, "4": {"4": 0.0875, "5": 0.6454, "1": 0.086, "6": 0.1266, "3": 0.0537, "2": 0.0008}, "5": {"5": 0.6694, "4": 0.0502, "6": 0.1763, "3": 0.0247, "1": 0.0795}, "6": {"5": 0.5855, "4": 0.0691, "3": 0.0187, "6": 0.2377, "1": 0.089}}}, {"model": "utter-project/EuroLLM-9B-Instruct-2512", "avg_exact": 0.205604, "avg_wp": 0.316168, "avg_bias": 1.7841, "avg_parsed": 0.999874, "avg_mae": 2.0126, "total": 7923, "lang_exact": {"ab": 0.239631, "cn": 0.212844, "cy": 0.219959, "de": 0.157068, "en": 0.136771, "es": 0.235727, "eu": 0.188679, "fr": 0.194946, "gl": 0.197292, "he": 0.171111, "hi": 0.233886, "ir": 0.253359, "kz": 0.102041, "la": 0.534722, "pl": 0.213144, "sl": 0.195777, "uk": 0.177489}, "lang_wp": {"ab": 0.35023, "cn": 0.317431, "cy": 0.385947, "de": 0.254799, "en": 0.25, "es": 0.346225, "eu": 0.295148, "fr": 0.311372, "gl": 0.296905, "he": 0.278889, "hi": 0.3407, "ir": 0.37524, "kz": 0.265306, "la": 0.604167, "pl": 0.29929, "sl": 0.287908, "uk": 0.287879}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 0.997963, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.9885, "cn": 2.0661, "cy": 1.5184, "de": 2.3874, "en": 2.0987, "es": 1.8858, "eu": 2.0377, "fr": 2.0018, "gl": 2.0406, "he": 2.1822, "hi": 2.0166, "ir": 1.7332, "kz": 1.8612, "la": 1.1319, "pl": 2.2274, "sl": 2.2188, "uk": 2.0649}, "confusion": {"1": {"6": 0.4478, "1": 0.294, "3": 0.0907, "2": 0.0833, "5": 0.0815, "4": 0.0027}, "2": {"1": 0.068, "3": 0.1003, "6": 0.7127, "2": 0.0536, "5": 0.0605, "4": 0.0048}, "3": {"6": 0.8115, "1": 0.0237, "2": 0.0245, "3": 0.0827, "5": 0.0532, "4": 0.0043}, "4": {"6": 0.8735, "2": 0.0102, "1": 0.0177, "3": 0.0633, "5": 0.0327, "4": 0.0027}, "5": {"6": 0.9033, "3": 0.0536, "5": 0.0186, "1": 0.0186, "2": 0.006}, "6": {"6": 0.9274, "1": 0.0111, "3": 0.0384, "5": 0.0179, "2": 0.0017, "4": 0.0034}}}, {"model": "CYFRAGOVPL/pllum-12b-nc-chat-250715", "avg_exact": 0.107897, "avg_wp": 0.186483, "avg_bias": -0.1812, "avg_parsed": 0.554114, "avg_mae": 1.9248, "total": 9092, "lang_exact": {"ab": 0.093333, "cn": 0.11, "cy": 0.1625, "de": 0.111667, "en": 0.099808, "es": 0.11, "eu": 0.077922, "fr": 0.113333, "gl": 0.119231, "he": 0.085, "hi": 0.12, "ir": 0.080756, "kz": 0.088415, "la": 0.15873, "pl": 0.125, "sl": 0.096667, "uk": 0.103774}, "lang_wp": {"ab": 0.17, "cn": 0.180833, "cy": 0.283929, "de": 0.180833, "en": 0.179463, "es": 0.165833, "eu": 0.15368, "fr": 0.199167, "gl": 0.232692, "he": 0.154167, "hi": 0.1975, "ir": 0.150344, "kz": 0.185976, "la": 0.224868, "pl": 0.185833, "sl": 0.168333, "uk": 0.185849}, "lang_parsed": {"ab": 0.49, "cn": 0.528333, "cy": 0.789286, "de": 0.481667, "en": 0.495202, "es": 0.443333, "eu": 0.649351, "fr": 0.551667, "gl": 0.548077, "he": 0.493333, "hi": 0.586667, "ir": 0.594502, "kz": 0.631098, "la": 0.666667, "pl": 0.541667, "sl": 0.546667, "uk": 0.520755}, "lang_mae": {"ab": 1.8503, "cn": 2.0158, "cy": 1.7421, "de": 1.8478, "en": 1.8023, "es": 1.7556, "eu": 2.4033, "fr": 1.7976, "gl": 1.5123, "he": 2.0101, "hi": 1.9062, "ir": 2.2168, "kz": 1.9179, "la": 2.3413, "pl": 1.9938, "sl": 2.0305, "uk": 1.7826}, "confusion": {"1": {"6": 0.229, "3": 0.0519, "1": 0.5224, "2": 0.1055, "5": 0.0376, "4": 0.0537}, "2": {"3": 0.0562, "4": 0.1054, "6": 0.2799, "1": 0.363, "5": 0.0843, "2": 0.1112}, "3": {"1": 0.2962, "4": 0.1346, "3": 0.071, "2": 0.0783, "6": 0.295, "5": 0.1248}, "4": {"2": 0.0586, "1": 0.2669, "4": 0.1476, "3": 0.0779, "5": 0.1547, "6": 0.2942}, "5": {"5": 0.1895, "4": 0.1581, "1": 0.2555, "6": 0.3026, "2": 0.0513, "3": 0.0429}, "6": {"4": 0.14, "5": 0.1944, "6": 0.2419, "3": 0.0521, "1": 0.3206, "2": 0.0509}}}, {"model": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "avg_exact": 0.094012, "avg_wp": 0.168646, "avg_bias": 0.3332, "avg_parsed": 0.36242, "avg_mae": 1.2653, "total": 7999, "lang_exact": {"ab": 0.105618, "cn": 0.092593, "cy": 0.104628, "de": 0.099476, "en": 0.098468, "es": 0.09375, "eu": 0.078329, "fr": 0.129032, "gl": 0.090909, "he": 0.080078, "hi": 0.111111, "ir": 0.088933, "kz": 0.111538, "la": 0.034722, "pl": 0.06295, "sl": 0.101727, "uk": 0.074725}, "lang_wp": {"ab": 0.186517, "cn": 0.167593, "cy": 0.165996, "de": 0.173647, "en": 0.173961, "es": 0.176471, "eu": 0.159269, "fr": 0.206093, "gl": 0.166344, "he": 0.158203, "hi": 0.19774, "ir": 0.153162, "kz": 0.201923, "la": 0.059028, "pl": 0.130396, "sl": 0.177543, "uk": 0.146154}, "lang_parsed": {"ab": 0.4, "cn": 0.366667, "cy": 0.331992, "de": 0.354276, "en": 0.371991, "es": 0.380515, "eu": 0.318538, "fr": 0.399642, "gl": 0.353965, "he": 0.378906, "hi": 0.416196, "ir": 0.326087, "kz": 0.415385, "la": 0.201389, "pl": 0.31295, "sl": 0.414587, "uk": 0.314286}, "lang_mae": {"ab": 1.3034, "cn": 1.2778, "cy": 1.2, "de": 1.1527, "en": 1.2647, "es": 1.2367, "eu": 1.1803, "fr": 1.148, "gl": 1.2623, "he": 1.3557, "hi": 1.2579, "ir": 1.2485, "kz": 1.2315, "la": 2.0345, "pl": 1.3563, "sl": 1.4074, "uk": 1.1888}, "confusion": {"1": {"5": 0.1048, "1": 0.3238, "3": 0.1683, "4": 0.2127, "6": 0.0381, "2": 0.1524}, "2": {"5": 0.3046, "1": 0.1996, "3": 0.0966, "6": 0.0231, "2": 0.0987, "4": 0.2773}, "3": {"2": 0.0522, "3": 0.0703, "5": 0.3775, "4": 0.3735, "1": 0.0904, "6": 0.0361}, "4": {"5": 0.5109, "4": 0.2945, "1": 0.0782, "2": 0.0382, "6": 0.0455, "3": 0.0327}, "5": {"5": 0.6578, "4": 0.1765, "6": 0.0606, "1": 0.0588, "3": 0.0285, "2": 0.0178}, "6": {"5": 0.7234, "4": 0.1263, "3": 0.006, "1": 0.0441, "2": 0.0261, "6": 0.0741}}}];
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 = 150881;
300
 
301
  function langName(c) { return LANG_NAMES[c] || c.toUpperCase(); }
302
 
 
292
 
293
  // second dataset
294
  const HAS_SECOND = true;
295
+ const ALL_ROWS_2 = [{"model": "Qwen/Qwen3.5-397B-A17B-FP8", "avg_exact": 0.467554, "avg_wp": 0.660086, "avg_bias": 0.4369, "avg_parsed": 1.0, "avg_mae": 0.7244, "total": 9092, "lang_exact": {"ab": 0.463333, "cn": 0.438333, "cy": 0.332143, "de": 0.551667, "en": 0.587332, "es": 0.57, "eu": 0.38961, "fr": 0.54, "gl": 0.453846, "he": 0.493333, "hi": 0.513333, "ir": 0.40378, "kz": 0.362805, "la": 0.433862, "pl": 0.423333, "sl": 0.395, "uk": 0.516981}, "lang_wp": {"ab": 0.644167, "cn": 0.640833, "cy": 0.528571, "de": 0.725, "en": 0.759117, "es": 0.7425, "eu": 0.574675, "fr": 0.731667, "gl": 0.646154, "he": 0.695, "hi": 0.703333, "ir": 0.607388, "kz": 0.591463, "la": 0.664021, "pl": 0.606667, "sl": 0.608333, "uk": 0.711321}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 0.78, "cn": 0.75, "cy": 1.0071, "de": 0.5783, "en": 0.4952, "es": 0.5383, "eu": 0.9351, "fr": 0.5533, "gl": 0.7654, "he": 0.6333, "hi": 0.6133, "ir": 0.8196, "kz": 0.875, "la": 0.6931, "pl": 0.9333, "sl": 0.83, "uk": 0.5906}, "confusion": {"1": {"1": 0.6019, "2": 0.3257, "4": 0.0426, "6": 0.0162, "3": 0.0068, "5": 0.0068}, "2": {"2": 0.4974, "4": 0.2436, "3": 0.0713, "1": 0.0925, "6": 0.0257, "5": 0.0694}, "3": {"2": 0.2051, "3": 0.0857, "4": 0.4609, "1": 0.0121, "6": 0.0364, "5": 0.1997}, "4": {"2": 0.0587, "5": 0.4404, "6": 0.1144, "4": 0.3651, "3": 0.0202, "1": 0.0012}, "5": {"6": 0.4461, "4": 0.096, "5": 0.4368, "2": 0.0173, "3": 0.0037}, "6": {"6": 0.8223, "5": 0.1526, "4": 0.0221, "2": 0.0031}}}, {"model": "mistralai/Mistral-Small-24B-Instruct-2501", "avg_exact": 0.31779, "avg_wp": 0.560195, "avg_bias": 0.0284, "avg_parsed": 1.0, "avg_mae": 0.9057, "total": 7999, "lang_exact": {"ab": 0.294382, "cn": 0.307407, "cy": 0.321932, "de": 0.336824, "en": 0.415755, "es": 0.382353, "eu": 0.289817, "fr": 0.302867, "gl": 0.305609, "he": 0.306641, "hi": 0.241055, "ir": 0.272727, "kz": 0.376923, "la": 0.319444, "pl": 0.341727, "sl": 0.295585, "uk": 0.318681}, "lang_wp": {"ab": 0.529213, "cn": 0.544444, "cy": 0.560362, "de": 0.576789, "en": 0.671772, "es": 0.639706, "eu": 0.523499, "fr": 0.580645, "gl": 0.56383, "he": 0.544922, "hi": 0.461394, "ir": 0.513834, "kz": 0.621154, "la": 0.402778, "pl": 0.570144, "sl": 0.536468, "uk": 0.596703}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 0.9843, "cn": 0.963, "cy": 0.8954, "de": 0.8709, "en": 0.6718, "es": 0.7243, "eu": 0.9687, "fr": 0.8548, "gl": 0.8878, "he": 0.9414, "hi": 1.1337, "ir": 1.0099, "kz": 0.7577, "la": 1.3056, "pl": 0.8759, "sl": 0.9539, "uk": 0.8154}, "confusion": {"3": {"4": 0.5322, "2": 0.0946, "3": 0.346, "1": 0.01, "6": 0.0007, "5": 0.0165}, "2": {"4": 0.3167, "2": 0.2579, "3": 0.4001, "1": 0.0219, "5": 0.0034}, "1": {"2": 0.4823, "3": 0.2102, "1": 0.2138, "4": 0.0919, "6": 0.0018}, "4": {"4": 0.6669, "3": 0.2057, "2": 0.0512, "5": 0.0708, "1": 0.0054}, "5": {"4": 0.5988, "5": 0.3031, "3": 0.0791, "2": 0.0132, "6": 0.0059}, "6": {"4": 0.399, "5": 0.5197, "3": 0.0335, "6": 0.0369, "2": 0.0075, "1": 0.0034}}}, {"model": "allenai/Olmo-3.1-32B-Instruct", "avg_exact": 0.35418, "avg_wp": 0.549877, "avg_bias": 0.6144, "avg_parsed": 1.0, "avg_mae": 1.0553, "total": 7739, "lang_exact": {"ab": 0.355499, "cn": 0.368715, "cy": 0.346154, "de": 0.37766, "en": 0.369892, "es": 0.468635, "eu": 0.312668, "fr": 0.4, "gl": 0.321569, "he": 0.281319, "hi": 0.357853, "ir": 0.348606, "kz": 0.164444, "la": 0.464789, "pl": 0.388385, "sl": 0.327485, "uk": 0.295943}, "lang_wp": {"ab": 0.528133, "cn": 0.566108, "cy": 0.552632, "de": 0.575355, "en": 0.563441, "es": 0.664207, "eu": 0.494609, "fr": 0.597297, "gl": 0.52549, "he": 0.497802, "hi": 0.549702, "ir": 0.557769, "kz": 0.386667, "la": 0.489437, "pl": 0.595281, "sl": 0.515595, "uk": 0.502387}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.202, "cn": 0.9777, "cy": 1.0223, "de": 1.0018, "en": 1.0817, "es": 0.7583, "eu": 1.1968, "fr": 0.9099, "gl": 1.1, "he": 1.1231, "hi": 1.0676, "ir": 0.9622, "kz": 1.44, "la": 1.8592, "pl": 0.9274, "sl": 1.1384, "uk": 1.1074}, "confusion": {"1": {"1": 0.5078, "6": 0.0683, "3": 0.1588, "2": 0.2133, "5": 0.0185, "4": 0.0332}, "2": {"1": 0.1237, "3": 0.3462, "4": 0.1493, "5": 0.0891, "2": 0.1465, "6": 0.1451}, "3": {"1": 0.0211, "2": 0.0605, "6": 0.1355, "3": 0.3336, "4": 0.2658, "5": 0.1835}, "4": {"5": 0.2575, "3": 0.2026, "4": 0.2484, "6": 0.2498, "2": 0.0236, "1": 0.018}, "5": {"4": 0.1315, "6": 0.5058, "5": 0.2848, "3": 0.0623, "1": 0.0086, "2": 0.007}, "6": {"6": 0.718, "5": 0.1694, "4": 0.0613, "3": 0.027, "2": 0.0009, "1": 0.0234}}}, {"model": "speakleash/Bielik-11B-v3.0-Instruct", "avg_exact": 0.319321, "avg_wp": 0.52795, "avg_bias": -0.0152, "avg_parsed": 0.967946, "avg_mae": 1.0378, "total": 9016, "lang_exact": {"ab": 0.263525, "cn": 0.406518, "cy": 0.264286, "de": 0.366667, "en": 0.341651, "es": 0.446667, "eu": 0.244589, "fr": 0.433333, "gl": 0.290385, "he": 0.22031, "hi": 0.282794, "ir": 0.333333, "kz": 0.335366, "la": 0.243386, "pl": 0.193333, "sl": 0.311667, "uk": 0.388679}, "lang_wp": {"ab": 0.426702, "cn": 0.626072, "cy": 0.502679, "de": 0.595, "en": 0.587332, "es": 0.6625, "eu": 0.462121, "fr": 0.665, "gl": 0.524038, "he": 0.36747, "hi": 0.459114, "ir": 0.542955, "kz": 0.573171, "la": 0.402116, "pl": 0.3625, "sl": 0.524167, "uk": 0.619811}, "lang_parsed": {"ab": 0.900524, "cn": 0.96741, "cy": 1.0, "de": 0.996667, "en": 0.994242, "es": 0.995, "eu": 0.980519, "fr": 1.0, "gl": 1.0, "he": 0.977625, "hi": 0.938671, "ir": 0.998282, "kz": 0.990854, "la": 0.994709, "pl": 0.903333, "sl": 0.933333, "uk": 0.916981}, "lang_mae": {"ab": 1.2868, "cn": 0.7695, "cy": 1.0911, "de": 0.8645, "en": 0.8842, "es": 0.6851, "eu": 1.2075, "fr": 0.6867, "gl": 1.0038, "he": 1.5933, "hi": 1.1887, "ir": 0.9725, "kz": 0.9046, "la": 2.0904, "pl": 1.4963, "sl": 0.9571, "uk": 0.6667}, "confusion": {"1": {"1": 0.748, "5": 0.0537, "2": 0.0661, "6": 0.0018, "4": 0.096, "3": 0.0344}, "2": {"2": 0.1071, "1": 0.2756, "3": 0.1783, "5": 0.128, "4": 0.3109}, "3": {"1": 0.1199, "4": 0.4262, "5": 0.2148, "3": 0.1816, "2": 0.0575}, "4": {"1": 0.0789, "4": 0.3598, "5": 0.428, "3": 0.1086, "2": 0.024, "6": 0.0006}, "5": {"3": 0.0566, "4": 0.2227, "1": 0.0436, "5": 0.6719, "2": 0.0052}, "6": {"5": 0.7356, "1": 0.0781, "3": 0.0374, "4": 0.1422, "2": 0.0053, "6": 0.0013}}}, {"model": "Qwen/Qwen2.5-14B-Instruct", "avg_exact": 0.278385, "avg_wp": 0.516447, "avg_bias": 0.053, "avg_parsed": 1.0, "avg_mae": 0.9821, "total": 7874, "lang_exact": {"ab": 0.253968, "cn": 0.291367, "cy": 0.308316, "de": 0.278571, "en": 0.324561, "es": 0.305556, "eu": 0.248649, "fr": 0.337545, "gl": 0.252964, "he": 0.276062, "hi": 0.226824, "ir": 0.282869, "kz": 0.341772, "la": 0.262411, "pl": 0.21558, "sl": 0.268627, "uk": 0.269142}, "lang_wp": {"ab": 0.503401, "cn": 0.555755, "cy": 0.548682, "de": 0.5125, "en": 0.569079, "es": 0.557407, "eu": 0.467568, "fr": 0.563177, "gl": 0.499012, "he": 0.52027, "hi": 0.455621, "ir": 0.513944, "kz": 0.586498, "la": 0.358156, "pl": 0.447464, "sl": 0.510784, "uk": 0.520882}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.0113, "cn": 0.8903, "cy": 0.9148, "de": 0.9839, "en": 0.8684, "es": 0.8889, "eu": 1.0973, "fr": 0.8809, "gl": 1.0158, "he": 0.9807, "hi": 1.1144, "ir": 1.0, "kz": 0.827, "la": 1.3333, "pl": 1.125, "sl": 1.0039, "uk": 0.9606}, "confusion": {"1": {"1": 0.1435, "2": 0.4625, "3": 0.3373, "4": 0.0567}, "2": {"3": 0.4684, "2": 0.1699, "4": 0.3432, "1": 0.011, "5": 0.0076}, "3": {"4": 0.5922, "2": 0.049, "3": 0.3429, "5": 0.0144, "1": 0.0007, "6": 0.0007}, "4": {"4": 0.7609, "3": 0.1776, "5": 0.043, "2": 0.0178, "6": 0.0007}, "5": {"4": 0.8014, "5": 0.143, "3": 0.0504, "2": 0.003, "6": 0.0023}, "6": {"5": 0.2314, "4": 0.7293, "6": 0.007, "3": 0.0297, "2": 0.0026}}}, {"model": "utter-project/EuroLLM-22B-Instruct-2512", "avg_exact": 0.298877, "avg_wp": 0.513694, "avg_bias": 0.574, "avg_parsed": 0.999874, "avg_mae": 1.1195, "total": 7923, "lang_exact": {"ab": 0.361751, "cn": 0.33945, "cy": 0.254582, "de": 0.326353, "en": 0.253363, "es": 0.368324, "eu": 0.22372, "fr": 0.389892, "gl": 0.294004, "he": 0.257778, "hi": 0.302026, "ir": 0.351248, "kz": 0.293878, "la": 0.194444, "pl": 0.216696, "sl": 0.272553, "uk": 0.266234}, "lang_wp": {"ab": 0.570276, "cn": 0.569725, "cy": 0.482688, "de": 0.546248, "en": 0.439462, "es": 0.581952, "eu": 0.443396, "fr": 0.591155, "gl": 0.525145, "he": 0.444444, "hi": 0.524862, "ir": 0.56238, "kz": 0.504082, "la": 0.524306, "pl": 0.409414, "sl": 0.482726, "uk": 0.492424}, "lang_parsed": {"ab": 1.0, "cn": 0.998165, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 0.9401, "cn": 0.9154, "cy": 1.1527, "de": 1.0489, "en": 1.3161, "es": 0.9134, "eu": 1.3477, "fr": 0.9206, "gl": 1.0387, "he": 1.3711, "hi": 1.0829, "ir": 0.9712, "kz": 1.1796, "la": 1.2083, "pl": 1.4938, "sl": 1.2054, "uk": 1.132}, "confusion": {"2": {"1": 0.068, "5": 0.455, "2": 0.3491, "4": 0.0034, "3": 0.1203, "6": 0.0041}, "1": {"1": 0.3846, "2": 0.4139, "5": 0.1465, "3": 0.0513, "6": 0.0037}, "3": {"5": 0.7158, "2": 0.1568, "1": 0.018, "3": 0.1065, "6": 0.0022, "4": 0.0007}, "4": {"5": 0.8645, "2": 0.0735, "3": 0.049, "4": 0.0027, "6": 0.0027, "1": 0.0075}, "5": {"5": 0.936, "2": 0.0387, "3": 0.0097, "6": 0.0082, "1": 0.0045, "4": 0.003}, "6": {"5": 0.9403, "1": 0.0094, "6": 0.0256, "2": 0.0179, "4": 0.0017, "3": 0.0051}}}, {"model": "CYFRAGOVPL/Llama-PLLuM-70B-chat-250801", "avg_exact": 0.275562, "avg_wp": 0.474108, "avg_bias": -0.6122, "avg_parsed": 0.996364, "avg_mae": 1.2257, "total": 9076, "lang_exact": {"ab": 0.297479, "cn": 0.248333, "cy": 0.276786, "de": 0.363333, "en": 0.243762, "es": 0.295, "eu": 0.166667, "fr": 0.318333, "gl": 0.201923, "he": 0.243655, "hi": 0.281667, "ir": 0.262887, "kz": 0.303681, "la": 0.216931, "pl": 0.316667, "sl": 0.331667, "uk": 0.245283}, "lang_wp": {"ab": 0.485714, "cn": 0.39, "cy": 0.504464, "de": 0.561667, "en": 0.487524, "es": 0.491667, "eu": 0.376623, "fr": 0.511667, "gl": 0.414423, "he": 0.423012, "hi": 0.471667, "ir": 0.444158, "kz": 0.546012, "la": 0.304233, "pl": 0.520833, "sl": 0.5425, "uk": 0.471698}, "lang_parsed": {"ab": 0.986555, "cn": 1.0, "cy": 0.998214, "de": 1.0, "en": 0.992322, "es": 0.996667, "eu": 0.997835, "fr": 0.998333, "gl": 1.0, "he": 0.99154, "hi": 1.0, "ir": 0.994845, "kz": 0.996933, "la": 1.0, "pl": 0.993333, "sl": 0.996667, "uk": 0.998113}, "lang_mae": {"ab": 1.1806, "cn": 1.5733, "cy": 1.102, "de": 1.0117, "en": 1.1277, "es": 1.1488, "eu": 1.4967, "fr": 1.1002, "gl": 1.3058, "he": 1.3379, "hi": 1.2433, "ir": 1.3368, "kz": 1.0092, "la": 2.3439, "pl": 1.0419, "sl": 0.9916, "uk": 1.2042}, "confusion": {"1": {"3": 0.1541, "1": 0.786, "4": 0.0317, "5": 0.0154, "6": 0.0051, "2": 0.0077}, "2": {"3": 0.3323, "4": 0.1092, "1": 0.4874, "5": 0.0595, "2": 0.0071, "6": 0.0045}, "3": {"1": 0.3083, "3": 0.3807, "5": 0.1244, "4": 0.1765, "2": 0.0054, "6": 0.0047}, "4": {"4": 0.2148, "3": 0.3557, "5": 0.216, "1": 0.2037, "6": 0.0055, "2": 0.0043}, "5": {"5": 0.3859, "4": 0.2643, "3": 0.2506, "1": 0.0842, "2": 0.0044, "6": 0.0106}, "6": {"4": 0.2679, "3": 0.1772, "5": 0.4247, "1": 0.1019, "6": 0.0253, "2": 0.0031}}}, {"model": "mistralai/Mistral-Nemo-Instruct-2407", "avg_exact": 0.282611, "avg_wp": 0.468668, "avg_bias": -0.2413, "avg_parsed": 0.963425, "avg_mae": 1.2449, "total": 8011, "lang_exact": {"ab": 0.29148, "cn": 0.3, "cy": 0.181087, "de": 0.279232, "en": 0.323851, "es": 0.310662, "eu": 0.263708, "fr": 0.351254, "gl": 0.257253, "he": 0.289062, "hi": 0.265683, "ir": 0.243083, "kz": 0.296154, "la": 0.180556, "pl": 0.354317, "sl": 0.28215, "uk": 0.248352}, "lang_wp": {"ab": 0.483184, "cn": 0.492593, "cy": 0.343058, "de": 0.507853, "en": 0.507659, "es": 0.511949, "eu": 0.425587, "fr": 0.562724, "gl": 0.434236, "he": 0.487305, "hi": 0.417897, "ir": 0.380435, "kz": 0.457692, "la": 0.322917, "pl": 0.546763, "sl": 0.478887, "uk": 0.465934}, "lang_parsed": {"ab": 0.950673, "cn": 0.983333, "cy": 0.987928, "de": 0.95637, "en": 0.964989, "es": 0.977941, "eu": 0.942559, "fr": 0.958781, "gl": 0.912959, "he": 0.988281, "hi": 0.968635, "ir": 0.966403, "kz": 0.915385, "la": 0.9375, "pl": 0.992806, "sl": 0.955854, "uk": 0.967033}, "lang_mae": {"ab": 1.1085, "cn": 1.2298, "cy": 1.8045, "de": 1.042, "en": 1.0, "es": 1.1015, "eu": 1.3989, "fr": 0.8991, "gl": 1.2712, "he": 1.1739, "hi": 1.499, "ir": 1.5808, "kz": 1.1723, "la": 2.2148, "pl": 1.0145, "sl": 1.2129, "uk": 1.1795}, "confusion": {"1": {"1": 0.4749, "2": 0.3597, "5": 0.0799, "4": 0.0288, "3": 0.0483, "6": 0.0084}, "2": {"4": 0.1264, "2": 0.4316, "5": 0.176, "1": 0.1669, "3": 0.0866, "6": 0.0126}, "3": {"4": 0.2181, "1": 0.0934, "2": 0.3071, "3": 0.1225, "5": 0.248, "6": 0.0109}, "4": {"4": 0.2169, "2": 0.2479, "5": 0.3336, "1": 0.076, "3": 0.1105, "6": 0.0152}, "5": {"4": 0.1957, "2": 0.1995, "5": 0.4612, "1": 0.0491, "6": 0.0269, "3": 0.0675}, "6": {"5": 0.5312, "4": 0.1379, "2": 0.1544, "6": 0.0478, "1": 0.08, "3": 0.0487}}}, {"model": "Qwen/Qwen2.5-7B-Instruct", "avg_exact": 0.285497, "avg_wp": 0.461773, "avg_bias": 0.9564, "avg_parsed": 1.0, "avg_mae": 1.212, "total": 7874, "lang_exact": {"ab": 0.283447, "cn": 0.305755, "cy": 0.219067, "de": 0.341071, "en": 0.296053, "es": 0.362963, "eu": 0.267568, "fr": 0.370036, "gl": 0.304348, "he": 0.272201, "hi": 0.258383, "ir": 0.213147, "kz": 0.278481, "la": 0.35461, "pl": 0.286232, "sl": 0.190196, "uk": 0.266821}, "lang_wp": {"ab": 0.451247, "cn": 0.48741, "cy": 0.408722, "de": 0.525893, "en": 0.501096, "es": 0.531481, "eu": 0.422973, "fr": 0.546029, "gl": 0.503953, "he": 0.44305, "hi": 0.431953, "ir": 0.376494, "kz": 0.440928, "la": 0.574468, "pl": 0.429348, "sl": 0.347059, "uk": 0.472158}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.3107, "cn": 1.1259, "cy": 1.3266, "de": 1.0429, "en": 1.0658, "es": 1.0093, "eu": 1.3081, "fr": 0.9585, "gl": 1.0514, "he": 1.2838, "hi": 1.284, "ir": 1.4422, "kz": 1.1772, "la": 1.0, "pl": 1.4094, "sl": 1.5529, "uk": 1.1439}, "confusion": {"1": {"1": 0.3062, "3": 0.2678, "4": 0.3291, "6": 0.0283, "2": 0.0375, "5": 0.0311}, "2": {"2": 0.0186, "3": 0.1403, "4": 0.6272, "5": 0.1039, "1": 0.0413, "6": 0.0688}, "3": {"4": 0.611, "6": 0.1318, "2": 0.0029, "5": 0.2089, "3": 0.0389, "1": 0.0065}, "4": {"6": 0.2281, "4": 0.4597, "5": 0.2937, "3": 0.0143, "1": 0.0041}, "5": {"6": 0.4387, "4": 0.2092, "5": 0.3506, "3": 0.0015}, "6": {"6": 0.6052, "4": 0.1231, "5": 0.2681, "3": 0.0026, "1": 0.0009}}}, {"model": "speakleash/Bielik-11B-v2.6-Instruct", "avg_exact": 0.261933, "avg_wp": 0.461439, "avg_bias": 0.4995, "avg_parsed": 1.0, "avg_mae": 1.2414, "total": 8506, "lang_exact": {"ab": 0.214533, "cn": 0.250432, "cy": 0.219031, "de": 0.268456, "en": 0.321705, "es": 0.361204, "eu": 0.197397, "fr": 0.301667, "gl": 0.280769, "he": 0.238384, "hi": 0.23689, "ir": 0.183849, "kz": 0.206642, "la": 0.196721, "pl": 0.321667, "sl": 0.26, "uk": 0.280632}, "lang_wp": {"ab": 0.378893, "cn": 0.42228, "cy": 0.40754, "de": 0.466443, "en": 0.543605, "es": 0.574415, "eu": 0.439262, "fr": 0.526667, "gl": 0.523077, "he": 0.437374, "hi": 0.391501, "ir": 0.354811, "kz": 0.47417, "la": 0.289617, "pl": 0.498333, "sl": 0.438333, "uk": 0.530632}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.4948, "cn": 1.361, "cy": 1.3429, "de": 1.203, "en": 1.0039, "es": 0.903, "eu": 1.282, "fr": 0.9917, "gl": 1.0442, "he": 1.1636, "hi": 1.5461, "ir": 1.5155, "kz": 1.0701, "la": 1.9563, "pl": 1.315, "sl": 1.375, "uk": 1.0119}, "confusion": {"1": {"3": 0.653, "1": 0.2373, "6": 0.0874, "5": 0.0223}, "2": {"3": 0.7263, "5": 0.1183, "6": 0.1079, "1": 0.0195, "4": 0.028}, "3": {"3": 0.5543, "6": 0.1349, "5": 0.2886, "4": 0.0201, "1": 0.0021}, "4": {"3": 0.4415, "6": 0.1742, "5": 0.3612, "4": 0.0219, "1": 0.0013}, "6": {"3": 0.2302, "6": 0.3566, "5": 0.4009, "4": 0.0065, "1": 0.0058}, "5": {"5": 0.4329, "3": 0.2825, "6": 0.2621, "4": 0.0218, "2": 0.0007}}}, {"model": "allenai/Olmo-3-7B-Instruct", "avg_exact": 0.228195, "avg_wp": 0.409937, "avg_bias": 0.5317, "avg_parsed": 0.999612, "avg_mae": 1.4272, "total": 7739, "lang_exact": {"ab": 0.176471, "cn": 0.214153, "cy": 0.204453, "de": 0.23227, "en": 0.292473, "es": 0.287823, "eu": 0.221024, "fr": 0.23964, "gl": 0.264706, "he": 0.178022, "hi": 0.252485, "ir": 0.181275, "kz": 0.213333, "la": 0.211268, "pl": 0.257713, "sl": 0.163743, "uk": 0.250597}, "lang_wp": {"ab": 0.391304, "cn": 0.368715, "cy": 0.385628, "de": 0.437943, "en": 0.489247, "es": 0.511993, "eu": 0.392183, "fr": 0.423423, "gl": 0.431373, "he": 0.36044, "hi": 0.437376, "ir": 0.35757, "kz": 0.397778, "la": 0.31338, "pl": 0.434664, "sl": 0.309942, "uk": 0.435561}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 0.998227, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 0.998012, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 0.998185, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.3632, "cn": 1.5736, "cy": 1.4555, "de": 1.3091, "en": 1.1634, "es": 1.0996, "eu": 1.5553, "fr": 1.3892, "gl": 1.4078, "he": 1.5231, "hi": 1.3625, "ir": 1.498, "kz": 1.3911, "la": 1.7042, "pl": 1.4691, "sl": 1.8226, "uk": 1.3771}, "confusion": {"1": {"3": 0.2114, "4": 0.157, "2": 0.4035, "1": 0.0905, "5": 0.0766, "6": 0.0609}, "2": {"1": 0.027, "3": 0.1728, "4": 0.2122, "5": 0.1638, "6": 0.114, "2": 0.3103}, "3": {"3": 0.1151, "2": 0.2367, "4": 0.2251, "6": 0.1653, "5": 0.2535, "1": 0.0044}, "4": {"4": 0.1985, "3": 0.0985, "6": 0.2415, "2": 0.186, "5": 0.2741, "1": 0.0014}, "5": {"4": 0.1877, "6": 0.3879, "3": 0.0724, "5": 0.2033, "2": 0.148, "1": 0.0008}, "6": {"6": 0.4639, "5": 0.1597, "4": 0.1634, "3": 0.0731, "2": 0.139, "1": 0.0009}}}, {"model": "mistralai/Mistral-7B-Instruct-v0.3", "avg_exact": 0.229035, "avg_wp": 0.398141, "avg_bias": 0.9606, "avg_parsed": 0.994066, "avg_mae": 1.5188, "total": 7584, "lang_exact": {"ab": 0.224599, "cn": 0.208566, "cy": 0.220619, "de": 0.253142, "en": 0.16895, "es": 0.36194, "eu": 0.208914, "fr": 0.261993, "gl": 0.208791, "he": 0.199557, "hi": 0.240481, "ir": 0.197154, "kz": 0.228814, "la": 0.154412, "pl": 0.259191, "sl": 0.182711, "uk": 0.223502}, "lang_wp": {"ab": 0.415775, "cn": 0.388268, "cy": 0.371134, "de": 0.435368, "en": 0.326484, "es": 0.539179, "eu": 0.410864, "fr": 0.445572, "gl": 0.369231, "he": 0.379157, "hi": 0.403808, "ir": 0.327236, "kz": 0.427966, "la": 0.386029, "pl": 0.409007, "sl": 0.319253, "uk": 0.396313}, "lang_parsed": {"ab": 0.994652, "cn": 0.998138, "cy": 0.995876, "de": 0.994614, "en": 0.993151, "es": 0.994403, "eu": 0.997214, "fr": 0.99262, "gl": 0.997802, "he": 0.997783, "hi": 0.98998, "ir": 0.989837, "kz": 0.970339, "la": 0.977941, "pl": 1.0, "sl": 0.996071, "uk": 0.995392}, "lang_mae": {"ab": 1.371, "cn": 1.4981, "cy": 1.6418, "de": 1.37, "en": 1.7586, "es": 1.1032, "eu": 1.486, "fr": 1.3309, "gl": 1.5991, "he": 1.4422, "hi": 1.5668, "ir": 1.8029, "kz": 1.31, "la": 1.6692, "pl": 1.5625, "sl": 1.8679, "uk": 1.4769}, "confusion": {"2": {"4": 0.0677, "5": 0.3656, "1": 0.1214, "3": 0.2357, "2": 0.0247, "6": 0.1849}, "1": {"3": 0.2608, "1": 0.3499, "2": 0.0582, "5": 0.1839, "6": 0.1126, "4": 0.0347}, "4": {"3": 0.1364, "5": 0.4961, "4": 0.0473, "6": 0.2608, "1": 0.0382, "2": 0.0212}, "5": {"5": 0.5188, "2": 0.016, "3": 0.0721, "6": 0.3443, "4": 0.0328, "1": 0.016}, "3": {"5": 0.4767, "4": 0.0665, "3": 0.1663, "2": 0.0237, "6": 0.2106, "1": 0.0562}, "6": {"5": 0.4899, "4": 0.0308, "3": 0.0645, "6": 0.3744, "2": 0.0115, "1": 0.0289}}}, {"model": "cjvt/GaMS3-12B-Instruct", "avg_exact": 0.223201, "avg_wp": 0.38902, "avg_bias": 0.7368, "avg_parsed": 0.999876, "avg_mae": 1.4632, "total": 8060, "lang_exact": {"ab": 0.301339, "cn": 0.212613, "cy": 0.157258, "de": 0.217014, "en": 0.235931, "es": 0.210238, "eu": 0.18254, "fr": 0.183124, "gl": 0.223938, "he": 0.25, "hi": 0.268116, "ir": 0.200393, "kz": 0.155894, "la": 0.536913, "pl": 0.2375, "sl": 0.193858, "uk": 0.21692}, "lang_wp": {"ab": 0.459821, "cn": 0.364865, "cy": 0.336694, "de": 0.378472, "en": 0.452381, "es": 0.390311, "eu": 0.371693, "fr": 0.35368, "gl": 0.399614, "he": 0.436024, "hi": 0.424819, "ir": 0.311395, "kz": 0.368821, "la": 0.583893, "pl": 0.372321, "sl": 0.350288, "uk": 0.402386}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 0.997831}, "lang_mae": {"ab": 1.2612, "cn": 1.5964, "cy": 1.5323, "de": 1.5556, "en": 1.1645, "es": 1.3346, "eu": 1.4603, "fr": 1.4237, "gl": 1.444, "he": 1.2559, "hi": 1.3967, "ir": 1.8468, "kz": 1.4335, "la": 1.255, "pl": 1.7446, "sl": 1.5566, "uk": 1.3543}, "confusion": {"2": {"4": 0.3051, "1": 0.0567, "5": 0.2137, "3": 0.2594, "6": 0.1563, "2": 0.0089}, "3": {"4": 0.269, "5": 0.3915, "6": 0.1516, "3": 0.1715, "1": 0.0114, "2": 0.005}, "1": {"1": 0.3159, "6": 0.1182, "4": 0.1336, "3": 0.3655, "5": 0.0379, "2": 0.0289}, "4": {"4": 0.2047, "6": 0.1785, "3": 0.1604, "5": 0.4396, "1": 0.0114, "2": 0.0054}, "5": {"5": 0.3671, "4": 0.2143, "6": 0.2339, "3": 0.1752, "1": 0.0072, "2": 0.0022}, "6": {"6": 0.3165, "5": 0.2314, "4": 0.243, "3": 0.1901, "1": 0.0165, "2": 0.0025}}}, {"model": "swiss-ai/Apertus-8B-Instruct-2509", "avg_exact": 0.226841, "avg_wp": 0.368914, "avg_bias": 1.3785, "avg_parsed": 0.989763, "avg_mae": 1.7385, "total": 8010, "lang_exact": {"ab": 0.238202, "cn": 0.22037, "cy": 0.205231, "de": 0.247818, "en": 0.207877, "es": 0.277574, "eu": 0.224543, "fr": 0.340502, "gl": 0.224371, "he": 0.132812, "hi": 0.208487, "ir": 0.20751, "kz": 0.165385, "la": 0.506944, "pl": 0.223022, "sl": 0.197697, "uk": 0.178022}, "lang_wp": {"ab": 0.347191, "cn": 0.387963, "cy": 0.325956, "de": 0.410122, "en": 0.364333, "es": 0.418199, "eu": 0.390339, "fr": 0.537634, "gl": 0.341393, "he": 0.24707, "hi": 0.353321, "ir": 0.368577, "kz": 0.35, "la": 0.548611, "pl": 0.317446, "sl": 0.330134, "uk": 0.331868}, "lang_parsed": {"ab": 0.966292, "cn": 0.998148, "cy": 0.993964, "de": 1.0, "en": 1.0, "es": 0.996324, "eu": 0.986945, "fr": 0.996416, "gl": 0.996132, "he": 0.986328, "hi": 0.990775, "ir": 0.998024, "kz": 0.903846, "la": 0.972222, "pl": 0.998201, "sl": 0.996161, "uk": 0.984615}, "lang_mae": {"ab": 1.8721, "cn": 1.5158, "cy": 1.913, "de": 1.5445, "en": 1.6893, "es": 1.4668, "eu": 1.6323, "fr": 1.0917, "gl": 1.8699, "he": 2.2693, "hi": 1.8994, "ir": 1.7446, "kz": 1.4723, "la": 1.3929, "pl": 2.1369, "sl": 1.8825, "uk": 1.8438}, "confusion": {"2": {"6": 0.5169, "3": 0.1884, "1": 0.0856, "2": 0.1304, "5": 0.0649, "4": 0.0138}, "1": {"6": 0.3163, "3": 0.2203, "1": 0.2477, "4": 0.0165, "5": 0.0238, "2": 0.1755}, "3": {"6": 0.6273, "3": 0.1288, "1": 0.0317, "2": 0.0791, "4": 0.0187, "5": 0.1144}, "4": {"6": 0.6785, "5": 0.1539, "3": 0.0828, "1": 0.0321, "4": 0.0178, "2": 0.0349}, "5": {"5": 0.1532, "6": 0.7654, "3": 0.0244, "1": 0.0222, "2": 0.0185, "4": 0.0163}, "6": {"6": 0.7995, "5": 0.1261, "2": 0.0068, "4": 0.0161, "3": 0.0279, "1": 0.0237}}}, {"model": "speakleash/Bielik-1.5B-v3.0-Instruct", "avg_exact": 0.206902, "avg_wp": 0.363133, "avg_bias": -0.3521, "avg_parsed": 0.999854, "avg_mae": 1.7134, "total": 6868, "lang_exact": {"ab": 0.178694, "cn": 0.230932, "cy": 0.164927, "de": 0.225746, "en": 0.265306, "es": 0.238921, "eu": 0.143258, "fr": 0.210832, "gl": 0.229167, "he": 0.174263, "hi": 0.178082, "ir": 0.164241, "kz": 0.114094, "la": 0.126866, "pl": 0.268078, "sl": 0.268537, "uk": 0.143791}, "lang_wp": {"ab": 0.302405, "cn": 0.377119, "cy": 0.317328, "de": 0.403918, "en": 0.452806, "es": 0.416185, "eu": 0.296348, "fr": 0.404255, "gl": 0.436343, "he": 0.323056, "hi": 0.286301, "ir": 0.277547, "kz": 0.288591, "la": 0.164179, "pl": 0.417989, "sl": 0.428858, "uk": 0.289216}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 0.997449, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 2.1512, "cn": 1.6589, "cy": 1.9019, "de": 1.5392, "en": 1.2506, "es": 1.4644, "eu": 2.014, "fr": 1.4255, "gl": 1.1968, "he": 1.8365, "hi": 2.2658, "ir": 2.1497, "kz": 2.0738, "la": 2.6493, "pl": 1.5185, "sl": 1.4469, "uk": 1.9869}, "confusion": {"1": {"1": 0.5015, "5": 0.2251, "6": 0.0336, "2": 0.0809, "4": 0.1333, "3": 0.0257}, "2": {"1": 0.4241, "5": 0.1975, "4": 0.2221, "2": 0.1047, "6": 0.0269, "3": 0.0247}, "3": {"1": 0.3597, "2": 0.0854, "5": 0.2182, "4": 0.2877, "3": 0.0253, "6": 0.0237}, "4": {"1": 0.3423, "5": 0.2571, "6": 0.0384, "4": 0.2678, "2": 0.0806, "3": 0.0138}, "5": {"1": 0.2749, "5": 0.3123, "6": 0.0447, "4": 0.2603, "2": 0.0868, "3": 0.021}, "6": {"1": 0.2752, "5": 0.3571, "2": 0.0539, "6": 0.0585, "4": 0.2307, "3": 0.0246}}}, {"model": "speakleash/Bielik-4.5B-v3.0-Instruct", "avg_exact": 0.188847, "avg_wp": 0.338818, "avg_bias": 1.1003, "avg_parsed": 1.0, "avg_mae": 1.7567, "total": 6868, "lang_exact": {"ab": 0.154639, "cn": 0.152542, "cy": 0.17119, "de": 0.169776, "en": 0.191327, "es": 0.22158, "eu": 0.129213, "fr": 0.193424, "gl": 0.196759, "he": 0.201072, "hi": 0.191781, "ir": 0.2079, "kz": 0.255034, "la": 0.462687, "pl": 0.17284, "sl": 0.162325, "uk": 0.202614}, "lang_wp": {"ab": 0.286942, "cn": 0.313559, "cy": 0.331942, "de": 0.29291, "en": 0.359694, "es": 0.32948, "eu": 0.29073, "fr": 0.330754, "gl": 0.359954, "he": 0.348525, "hi": 0.349315, "ir": 0.373181, "kz": 0.489933, "la": 0.55597, "pl": 0.324515, "sl": 0.313627, "uk": 0.367647}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 1.0, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.8007, "cn": 1.786, "cy": 1.739, "de": 1.9888, "en": 1.5357, "es": 1.9094, "eu": 2.0674, "fr": 1.7988, "gl": 1.5995, "he": 1.6756, "hi": 1.7342, "ir": 1.5738, "kz": 1.1812, "la": 1.2015, "pl": 1.8554, "sl": 1.8858, "uk": 1.6471}, "confusion": {"2": {"4": 0.1429, "5": 0.6133, "1": 0.101, "3": 0.0868, "6": 0.0561}, "3": {"5": 0.6411, "4": 0.1186, "1": 0.0822, "6": 0.0909, "3": 0.0672}, "1": {"1": 0.1598, "4": 0.1696, "5": 0.5276, "3": 0.1016, "6": 0.0414}, "4": {"4": 0.0875, "5": 0.6454, "1": 0.086, "6": 0.1266, "3": 0.0537, "2": 0.0008}, "5": {"5": 0.6694, "4": 0.0502, "6": 0.1763, "3": 0.0247, "1": 0.0795}, "6": {"5": 0.5855, "4": 0.0691, "3": 0.0187, "6": 0.2377, "1": 0.089}}}, {"model": "utter-project/EuroLLM-9B-Instruct-2512", "avg_exact": 0.205604, "avg_wp": 0.316168, "avg_bias": 1.7841, "avg_parsed": 0.999874, "avg_mae": 2.0126, "total": 7923, "lang_exact": {"ab": 0.239631, "cn": 0.212844, "cy": 0.219959, "de": 0.157068, "en": 0.136771, "es": 0.235727, "eu": 0.188679, "fr": 0.194946, "gl": 0.197292, "he": 0.171111, "hi": 0.233886, "ir": 0.253359, "kz": 0.102041, "la": 0.534722, "pl": 0.213144, "sl": 0.195777, "uk": 0.177489}, "lang_wp": {"ab": 0.35023, "cn": 0.317431, "cy": 0.385947, "de": 0.254799, "en": 0.25, "es": 0.346225, "eu": 0.295148, "fr": 0.311372, "gl": 0.296905, "he": 0.278889, "hi": 0.3407, "ir": 0.37524, "kz": 0.265306, "la": 0.604167, "pl": 0.29929, "sl": 0.287908, "uk": 0.287879}, "lang_parsed": {"ab": 1.0, "cn": 1.0, "cy": 0.997963, "de": 1.0, "en": 1.0, "es": 1.0, "eu": 1.0, "fr": 1.0, "gl": 1.0, "he": 1.0, "hi": 1.0, "ir": 1.0, "kz": 1.0, "la": 1.0, "pl": 1.0, "sl": 1.0, "uk": 1.0}, "lang_mae": {"ab": 1.9885, "cn": 2.0661, "cy": 1.5184, "de": 2.3874, "en": 2.0987, "es": 1.8858, "eu": 2.0377, "fr": 2.0018, "gl": 2.0406, "he": 2.1822, "hi": 2.0166, "ir": 1.7332, "kz": 1.8612, "la": 1.1319, "pl": 2.2274, "sl": 2.2188, "uk": 2.0649}, "confusion": {"1": {"6": 0.4478, "1": 0.294, "3": 0.0907, "2": 0.0833, "5": 0.0815, "4": 0.0027}, "2": {"1": 0.068, "3": 0.1003, "6": 0.7127, "2": 0.0536, "5": 0.0605, "4": 0.0048}, "3": {"6": 0.8115, "1": 0.0237, "2": 0.0245, "3": 0.0827, "5": 0.0532, "4": 0.0043}, "4": {"6": 0.8735, "2": 0.0102, "1": 0.0177, "3": 0.0633, "5": 0.0327, "4": 0.0027}, "5": {"6": 0.9033, "3": 0.0536, "5": 0.0186, "1": 0.0186, "2": 0.006}, "6": {"6": 0.9274, "1": 0.0111, "3": 0.0384, "5": 0.0179, "2": 0.0017, "4": 0.0034}}}, {"model": "CYFRAGOVPL/pllum-12b-nc-chat-250715", "avg_exact": 0.107897, "avg_wp": 0.186483, "avg_bias": -0.1812, "avg_parsed": 0.554114, "avg_mae": 1.9248, "total": 9092, "lang_exact": {"ab": 0.093333, "cn": 0.11, "cy": 0.1625, "de": 0.111667, "en": 0.099808, "es": 0.11, "eu": 0.077922, "fr": 0.113333, "gl": 0.119231, "he": 0.085, "hi": 0.12, "ir": 0.080756, "kz": 0.088415, "la": 0.15873, "pl": 0.125, "sl": 0.096667, "uk": 0.103774}, "lang_wp": {"ab": 0.17, "cn": 0.180833, "cy": 0.283929, "de": 0.180833, "en": 0.179463, "es": 0.165833, "eu": 0.15368, "fr": 0.199167, "gl": 0.232692, "he": 0.154167, "hi": 0.1975, "ir": 0.150344, "kz": 0.185976, "la": 0.224868, "pl": 0.185833, "sl": 0.168333, "uk": 0.185849}, "lang_parsed": {"ab": 0.49, "cn": 0.528333, "cy": 0.789286, "de": 0.481667, "en": 0.495202, "es": 0.443333, "eu": 0.649351, "fr": 0.551667, "gl": 0.548077, "he": 0.493333, "hi": 0.586667, "ir": 0.594502, "kz": 0.631098, "la": 0.666667, "pl": 0.541667, "sl": 0.546667, "uk": 0.520755}, "lang_mae": {"ab": 1.8503, "cn": 2.0158, "cy": 1.7421, "de": 1.8478, "en": 1.8023, "es": 1.7556, "eu": 2.4033, "fr": 1.7976, "gl": 1.5123, "he": 2.0101, "hi": 1.9062, "ir": 2.2168, "kz": 1.9179, "la": 2.3413, "pl": 1.9938, "sl": 2.0305, "uk": 1.7826}, "confusion": {"1": {"6": 0.229, "3": 0.0519, "1": 0.5224, "2": 0.1055, "5": 0.0376, "4": 0.0537}, "2": {"3": 0.0562, "4": 0.1054, "6": 0.2799, "1": 0.363, "5": 0.0843, "2": 0.1112}, "3": {"1": 0.2962, "4": 0.1346, "3": 0.071, "2": 0.0783, "6": 0.295, "5": 0.1248}, "4": {"2": 0.0586, "1": 0.2669, "4": 0.1476, "3": 0.0779, "5": 0.1547, "6": 0.2942}, "5": {"5": 0.1895, "4": 0.1581, "1": 0.2555, "6": 0.3026, "2": 0.0513, "3": 0.0429}, "6": {"4": 0.14, "5": 0.1944, "6": 0.2419, "3": 0.0521, "1": 0.3206, "2": 0.0509}}}, {"model": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "avg_exact": 0.094012, "avg_wp": 0.168646, "avg_bias": 0.3332, "avg_parsed": 0.36242, "avg_mae": 1.2653, "total": 7999, "lang_exact": {"ab": 0.105618, "cn": 0.092593, "cy": 0.104628, "de": 0.099476, "en": 0.098468, "es": 0.09375, "eu": 0.078329, "fr": 0.129032, "gl": 0.090909, "he": 0.080078, "hi": 0.111111, "ir": 0.088933, "kz": 0.111538, "la": 0.034722, "pl": 0.06295, "sl": 0.101727, "uk": 0.074725}, "lang_wp": {"ab": 0.186517, "cn": 0.167593, "cy": 0.165996, "de": 0.173647, "en": 0.173961, "es": 0.176471, "eu": 0.159269, "fr": 0.206093, "gl": 0.166344, "he": 0.158203, "hi": 0.19774, "ir": 0.153162, "kz": 0.201923, "la": 0.059028, "pl": 0.130396, "sl": 0.177543, "uk": 0.146154}, "lang_parsed": {"ab": 0.4, "cn": 0.366667, "cy": 0.331992, "de": 0.354276, "en": 0.371991, "es": 0.380515, "eu": 0.318538, "fr": 0.399642, "gl": 0.353965, "he": 0.378906, "hi": 0.416196, "ir": 0.326087, "kz": 0.415385, "la": 0.201389, "pl": 0.31295, "sl": 0.414587, "uk": 0.314286}, "lang_mae": {"ab": 1.3034, "cn": 1.2778, "cy": 1.2, "de": 1.1527, "en": 1.2647, "es": 1.2367, "eu": 1.1803, "fr": 1.148, "gl": 1.2623, "he": 1.3557, "hi": 1.2579, "ir": 1.2485, "kz": 1.2315, "la": 2.0345, "pl": 1.3563, "sl": 1.4074, "uk": 1.1888}, "confusion": {"1": {"5": 0.1048, "1": 0.3238, "3": 0.1683, "4": 0.2127, "6": 0.0381, "2": 0.1524}, "2": {"5": 0.3046, "1": 0.1996, "3": 0.0966, "6": 0.0231, "2": 0.0987, "4": 0.2773}, "3": {"2": 0.0522, "3": 0.0703, "5": 0.3775, "4": 0.3735, "1": 0.0904, "6": 0.0361}, "4": {"5": 0.5109, "4": 0.2945, "1": 0.0782, "2": 0.0382, "6": 0.0455, "3": 0.0327}, "5": {"5": 0.6578, "4": 0.1765, "6": 0.0606, "1": 0.0588, "3": 0.0285, "2": 0.0178}, "6": {"5": 0.7234, "4": 0.1263, "3": 0.006, "1": 0.0441, "2": 0.0261, "6": 0.0741}}}];
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 = 153253;
300
 
301
  function langName(c) { return LANG_NAMES[c] || c.toUpperCase(); }
302