| { |
| "/fast/awuhrmann/agent-outputs/run-20260923-130458/7151de5c-aa35-48e2-8e49-b237efe92629/model": { |
| "amazon_de": { |
| "n": 900, |
| "acc": 0.7277777777777777, |
| "macro_f1": 0.731725988380043, |
| "conf": { |
| "negative": { |
| "negative": 237, |
| "neutral": 61, |
| "positive": 2 |
| }, |
| "neutral": { |
| "negative": 87, |
| "neutral": 195, |
| "positive": 18 |
| }, |
| "positive": { |
| "negative": 9, |
| "neutral": 68, |
| "positive": 223 |
| } |
| } |
| }, |
| "amazon_en": { |
| "n": 900, |
| "acc": 0.6933333333333334, |
| "macro_f1": 0.6968228288779286, |
| "conf": { |
| "negative": { |
| "negative": 214, |
| "neutral": 79, |
| "positive": 7 |
| }, |
| "neutral": { |
| "negative": 86, |
| "neutral": 180, |
| "positive": 34 |
| }, |
| "positive": { |
| "negative": 3, |
| "neutral": 67, |
| "positive": 230 |
| } |
| } |
| }, |
| "amazon_es": { |
| "n": 900, |
| "acc": 0.7088888888888889, |
| "macro_f1": 0.709468485921541, |
| "conf": { |
| "negative": { |
| "negative": 234, |
| "neutral": 60, |
| "positive": 6 |
| }, |
| "neutral": { |
| "negative": 71, |
| "neutral": 177, |
| "positive": 52 |
| }, |
| "positive": { |
| "negative": 5, |
| "neutral": 68, |
| "positive": 227 |
| } |
| } |
| }, |
| "amazon_fr": { |
| "n": 900, |
| "acc": 0.7166666666666667, |
| "macro_f1": 0.7180152772962751, |
| "conf": { |
| "negative": { |
| "negative": 227, |
| "neutral": 68, |
| "positive": 5 |
| }, |
| "neutral": { |
| "negative": 73, |
| "neutral": 185, |
| "positive": 42 |
| }, |
| "positive": { |
| "negative": 11, |
| "neutral": 56, |
| "positive": 233 |
| } |
| } |
| }, |
| "amazon_ja": { |
| "n": 900, |
| "acc": 0.6988888888888889, |
| "macro_f1": 0.7032127578700721, |
| "conf": { |
| "negative": { |
| "negative": 217, |
| "neutral": 79, |
| "positive": 4 |
| }, |
| "neutral": { |
| "negative": 55, |
| "neutral": 195, |
| "positive": 50 |
| }, |
| "positive": { |
| "negative": 7, |
| "neutral": 76, |
| "positive": 217 |
| } |
| } |
| }, |
| "amazon_zh": { |
| "n": 900, |
| "acc": 0.6111111111111112, |
| "macro_f1": 0.6106136052633455, |
| "conf": { |
| "negative": { |
| "negative": 239, |
| "neutral": 53, |
| "positive": 8 |
| }, |
| "neutral": { |
| "negative": 125, |
| "neutral": 153, |
| "positive": 22 |
| }, |
| "positive": { |
| "negative": 28, |
| "neutral": 114, |
| "positive": 158 |
| } |
| } |
| }, |
| "mteb_ara": { |
| "n": 600, |
| "acc": 0.8, |
| "macro_f1": 0.7999199679871949, |
| "conf": { |
| "negative": { |
| "negative": 234, |
| "positive": 66 |
| }, |
| "positive": { |
| "negative": 54, |
| "positive": 246 |
| } |
| } |
| }, |
| "mteb_bam": { |
| "n": 480, |
| "acc": 0.6166666666666667, |
| "macro_f1": 0.5787545787545788, |
| "conf": { |
| "negative": { |
| "negative": 76, |
| "positive": 104 |
| }, |
| "positive": { |
| "negative": 80, |
| "positive": 220 |
| } |
| } |
| }, |
| "mteb_bul": { |
| "n": 600, |
| "acc": 0.83, |
| "macro_f1": 0.8283964602563958, |
| "conf": { |
| "negative": { |
| "negative": 220, |
| "positive": 80 |
| }, |
| "positive": { |
| "negative": 22, |
| "positive": 278 |
| } |
| } |
| }, |
| "mteb_cmn": { |
| "n": 600, |
| "acc": 0.9116666666666666, |
| "macro_f1": 0.9111669809344227, |
| "conf": { |
| "negative": { |
| "negative": 251, |
| "positive": 49 |
| }, |
| "positive": { |
| "negative": 4, |
| "positive": 296 |
| } |
| } |
| }, |
| "mteb_cym": { |
| "n": 600, |
| "acc": 0.7216666666666667, |
| "macro_f1": 0.709038112522686, |
| "conf": { |
| "negative": { |
| "negative": 154, |
| "positive": 146 |
| }, |
| "positive": { |
| "negative": 21, |
| "positive": 279 |
| } |
| } |
| }, |
| "mteb_deu": { |
| "n": 513, |
| "acc": 0.8362573099415205, |
| "macro_f1": 0.8306930693069308, |
| "conf": { |
| "negative": { |
| "negative": 261, |
| "positive": 39 |
| }, |
| "positive": { |
| "negative": 45, |
| "positive": 168 |
| } |
| } |
| }, |
| "mteb_dza": { |
| "n": 92, |
| "acc": 0.8260869565217391, |
| "macro_f1": 0.8133874239350912, |
| "conf": { |
| "negative": { |
| "negative": 26, |
| "positive": 7 |
| }, |
| "positive": { |
| "negative": 9, |
| "positive": 50 |
| } |
| } |
| }, |
| "mteb_ell": { |
| "n": 600, |
| "acc": 0.7983333333333333, |
| "macro_f1": 0.7983327731465921, |
| "conf": { |
| "negative": { |
| "negative": 240, |
| "positive": 60 |
| }, |
| "positive": { |
| "negative": 61, |
| "positive": 239 |
| } |
| } |
| }, |
| "mteb_eng": { |
| "n": 600, |
| "acc": 0.8616666666666667, |
| "macro_f1": 0.8608125972984229, |
| "conf": { |
| "negative": { |
| "negative": 235, |
| "positive": 65 |
| }, |
| "positive": { |
| "negative": 18, |
| "positive": 282 |
| } |
| } |
| }, |
| "mteb_eus": { |
| "n": 227, |
| "acc": 0.9074889867841409, |
| "macro_f1": 0.8322955145118733, |
| "conf": { |
| "negative": { |
| "negative": 27, |
| "positive": 8 |
| }, |
| "positive": { |
| "negative": 13, |
| "positive": 179 |
| } |
| } |
| }, |
| "mteb_fas": { |
| "n": 600, |
| "acc": 0.79, |
| "macro_f1": 0.7884107294791993, |
| "conf": { |
| "negative": { |
| "negative": 263, |
| "positive": 37 |
| }, |
| "positive": { |
| "negative": 89, |
| "positive": 211 |
| } |
| } |
| }, |
| "mteb_fin": { |
| "n": 600, |
| "acc": 0.8583333333333333, |
| "macro_f1": 0.8576687253536652, |
| "conf": { |
| "negative": { |
| "negative": 237, |
| "positive": 63 |
| }, |
| "positive": { |
| "negative": 22, |
| "positive": 278 |
| } |
| } |
| }, |
| "mteb_heb": { |
| "n": 600, |
| "acc": 0.815, |
| "macro_f1": 0.8149871518855476, |
| "conf": { |
| "negative": { |
| "negative": 242, |
| "positive": 58 |
| }, |
| "positive": { |
| "negative": 53, |
| "positive": 247 |
| } |
| } |
| }, |
| "mteb_hrv": { |
| "n": 396, |
| "acc": 0.9242424242424242, |
| "macro_f1": 0.898989898989899, |
| "conf": { |
| "negative": { |
| "negative": 84, |
| "positive": 12 |
| }, |
| "positive": { |
| "negative": 18, |
| "positive": 282 |
| } |
| } |
| }, |
| "mteb_ind": { |
| "n": 600, |
| "acc": 0.9233333333333333, |
| "macro_f1": 0.9233026543950914, |
| "conf": { |
| "negative": { |
| "negative": 271, |
| "positive": 29 |
| }, |
| "positive": { |
| "negative": 17, |
| "positive": 283 |
| } |
| } |
| }, |
| "mteb_jpn": { |
| "n": 600, |
| "acc": 0.915, |
| "macro_f1": 0.9149808706959066, |
| "conf": { |
| "negative": { |
| "negative": 270, |
| "positive": 30 |
| }, |
| "positive": { |
| "negative": 21, |
| "positive": 279 |
| } |
| } |
| }, |
| "mteb_kor": { |
| "n": 600, |
| "acc": 0.78, |
| "macro_f1": 0.7793724371545729, |
| "conf": { |
| "negative": { |
| "negative": 218, |
| "positive": 82 |
| }, |
| "positive": { |
| "negative": 50, |
| "positive": 250 |
| } |
| } |
| }, |
| "mteb_mlt": { |
| "n": 171, |
| "acc": 0.8011695906432749, |
| "macro_f1": 0.7800393462469734, |
| "conf": { |
| "negative": { |
| "negative": 95, |
| "positive": 16 |
| }, |
| "positive": { |
| "negative": 18, |
| "positive": 42 |
| } |
| } |
| }, |
| "mteb_nor": { |
| "n": 417, |
| "acc": 0.8201438848920863, |
| "macro_f1": 0.7754732829359695, |
| "conf": { |
| "negative": { |
| "negative": 78, |
| "positive": 40 |
| }, |
| "positive": { |
| "negative": 35, |
| "positive": 264 |
| } |
| } |
| }, |
| "mteb_pol": { |
| "n": 480, |
| "acc": 0.95, |
| "macro_f1": 0.9495763008614049, |
| "conf": { |
| "negative": { |
| "negative": 250, |
| "positive": 21 |
| }, |
| "positive": { |
| "negative": 3, |
| "positive": 206 |
| } |
| } |
| }, |
| "mteb_rus": { |
| "n": 585, |
| "acc": 0.8854700854700854, |
| "macro_f1": 0.8850819042481141, |
| "conf": { |
| "negative": { |
| "negative": 242, |
| "positive": 43 |
| }, |
| "positive": { |
| "negative": 24, |
| "positive": 276 |
| } |
| } |
| }, |
| "mteb_slk": { |
| "n": 428, |
| "acc": 0.9322429906542056, |
| "macro_f1": 0.9186413125413775, |
| "conf": { |
| "negative": { |
| "negative": 112, |
| "positive": 16 |
| }, |
| "positive": { |
| "negative": 13, |
| "positive": 287 |
| } |
| } |
| }, |
| "mteb_spa": { |
| "n": 296, |
| "acc": 0.9391891891891891, |
| "macro_f1": 0.8899446418243411, |
| "conf": { |
| "negative": { |
| "negative": 40, |
| "positive": 12 |
| }, |
| "positive": { |
| "negative": 6, |
| "positive": 238 |
| } |
| } |
| }, |
| "mteb_tha": { |
| "n": 600, |
| "acc": 0.78, |
| "macro_f1": 0.7792912797761702, |
| "conf": { |
| "negative": { |
| "negative": 217, |
| "positive": 83 |
| }, |
| "positive": { |
| "negative": 49, |
| "positive": 251 |
| } |
| } |
| }, |
| "mteb_tur": { |
| "n": 211, |
| "acc": 0.8436018957345972, |
| "macro_f1": 0.8342971371457129, |
| "conf": { |
| "negative": { |
| "negative": 64, |
| "positive": 22 |
| }, |
| "positive": { |
| "negative": 11, |
| "positive": 114 |
| } |
| } |
| }, |
| "mteb_uig": { |
| "n": 400, |
| "acc": 0.7375, |
| "macro_f1": 0.6680130581530459, |
| "conf": { |
| "negative": { |
| "negative": 56, |
| "positive": 44 |
| }, |
| "positive": { |
| "negative": 61, |
| "positive": 239 |
| } |
| } |
| }, |
| "mteb_urd": { |
| "n": 294, |
| "acc": 0.7721088435374149, |
| "macro_f1": 0.7688326624496837, |
| "conf": { |
| "negative": { |
| "negative": 131, |
| "positive": 20 |
| }, |
| "positive": { |
| "negative": 47, |
| "positive": 96 |
| } |
| } |
| }, |
| "mteb_vie": { |
| "n": 600, |
| "acc": 0.8283333333333334, |
| "macro_f1": 0.8283328564801569, |
| "conf": { |
| "negative": { |
| "negative": 248, |
| "positive": 52 |
| }, |
| "positive": { |
| "negative": 51, |
| "positive": 249 |
| } |
| } |
| }, |
| "mteb_zho": { |
| "n": 600, |
| "acc": 0.8233333333333334, |
| "macro_f1": 0.8232076143035048, |
| "conf": { |
| "negative": { |
| "negative": 255, |
| "positive": 45 |
| }, |
| "positive": { |
| "negative": 61, |
| "positive": 239 |
| } |
| } |
| }, |
| "tweets_ar": { |
| "n": 870, |
| "acc": 0.6402298850574712, |
| "macro_f1": 0.6429980437884231, |
| "conf": { |
| "negative": { |
| "negative": 166, |
| "neutral": 91, |
| "positive": 33 |
| }, |
| "neutral": { |
| "negative": 43, |
| "neutral": 199, |
| "positive": 48 |
| }, |
| "positive": { |
| "negative": 13, |
| "neutral": 85, |
| "positive": 192 |
| } |
| } |
| }, |
| "tweets_en": { |
| "n": 870, |
| "acc": 0.7183908045977011, |
| "macro_f1": 0.7184236973215802, |
| "conf": { |
| "negative": { |
| "negative": 226, |
| "neutral": 58, |
| "positive": 6 |
| }, |
| "neutral": { |
| "negative": 82, |
| "neutral": 173, |
| "positive": 35 |
| }, |
| "positive": { |
| "negative": 20, |
| "neutral": 44, |
| "positive": 226 |
| } |
| } |
| }, |
| "tweets_fr": { |
| "n": 870, |
| "acc": 0.5942528735632184, |
| "macro_f1": 0.5876405489154494, |
| "conf": { |
| "negative": { |
| "negative": 179, |
| "neutral": 95, |
| "positive": 16 |
| }, |
| "neutral": { |
| "negative": 30, |
| "neutral": 227, |
| "positive": 33 |
| }, |
| "positive": { |
| "negative": 38, |
| "neutral": 141, |
| "positive": 111 |
| } |
| } |
| }, |
| "tweets_ge": { |
| "n": 870, |
| "acc": 0.6574712643678161, |
| "macro_f1": 0.6594983022179294, |
| "conf": { |
| "negative": { |
| "negative": 192, |
| "neutral": 78, |
| "positive": 20 |
| }, |
| "neutral": { |
| "negative": 56, |
| "neutral": 184, |
| "positive": 50 |
| }, |
| "positive": { |
| "negative": 30, |
| "neutral": 64, |
| "positive": 196 |
| } |
| } |
| }, |
| "tweets_hi": { |
| "n": 870, |
| "acc": 0.5540229885057472, |
| "macro_f1": 0.5551450228494298, |
| "conf": { |
| "negative": { |
| "negative": 139, |
| "neutral": 110, |
| "positive": 41 |
| }, |
| "neutral": { |
| "negative": 51, |
| "neutral": 181, |
| "positive": 58 |
| }, |
| "positive": { |
| "negative": 33, |
| "neutral": 95, |
| "positive": 162 |
| } |
| } |
| }, |
| "tweets_it": { |
| "n": 870, |
| "acc": 0.7045977011494253, |
| "macro_f1": 0.7034779421370988, |
| "conf": { |
| "negative": { |
| "negative": 185, |
| "neutral": 63, |
| "positive": 42 |
| }, |
| "neutral": { |
| "negative": 31, |
| "neutral": 194, |
| "positive": 65 |
| }, |
| "positive": { |
| "negative": 21, |
| "neutral": 35, |
| "positive": 234 |
| } |
| } |
| }, |
| "tweets_po": { |
| "n": 870, |
| "acc": 0.6022988505747127, |
| "macro_f1": 0.5855970768563793, |
| "conf": { |
| "negative": { |
| "negative": 165, |
| "neutral": 32, |
| "positive": 93 |
| }, |
| "neutral": { |
| "negative": 58, |
| "neutral": 104, |
| "positive": 128 |
| }, |
| "positive": { |
| "negative": 18, |
| "neutral": 17, |
| "positive": 255 |
| } |
| } |
| }, |
| "tweets_sp": { |
| "n": 870, |
| "acc": 0.6344827586206897, |
| "macro_f1": 0.6269295860603301, |
| "conf": { |
| "negative": { |
| "negative": 196, |
| "neutral": 59, |
| "positive": 35 |
| }, |
| "neutral": { |
| "negative": 73, |
| "neutral": 128, |
| "positive": 89 |
| }, |
| "positive": { |
| "negative": 19, |
| "neutral": 43, |
| "positive": 228 |
| } |
| } |
| }, |
| "_tweets_mean_f1": 0.6349637775183276, |
| "_amazon_mean_f1": 0.6949764906015342, |
| "_mteb_mean_f1": 0.822111770468087 |
| } |
| } |
