| { |
| "/fast/awuhrmann/agent-outputs/run-20260923-130458/82fa9d22-8b9d-4ee0-97c1-d7f9a4422ada/model": { |
| "amazon_de": { |
| "n": 900, |
| "acc": 0.74, |
| "macro_f1": 0.7442684103783481, |
| "conf": { |
| "negative": { |
| "negative": 240, |
| "neutral": 59, |
| "positive": 1 |
| }, |
| "neutral": { |
| "negative": 82, |
| "neutral": 201, |
| "positive": 17 |
| }, |
| "positive": { |
| "negative": 3, |
| "neutral": 72, |
| "positive": 225 |
| } |
| } |
| }, |
| "amazon_en": { |
| "n": 900, |
| "acc": 0.7022222222222222, |
| "macro_f1": 0.7054034088275136, |
| "conf": { |
| "negative": { |
| "negative": 225, |
| "neutral": 68, |
| "positive": 7 |
| }, |
| "neutral": { |
| "negative": 93, |
| "neutral": 180, |
| "positive": 27 |
| }, |
| "positive": { |
| "negative": 4, |
| "neutral": 69, |
| "positive": 227 |
| } |
| } |
| }, |
| "amazon_es": { |
| "n": 900, |
| "acc": 0.7255555555555555, |
| "macro_f1": 0.7230906138890525, |
| "conf": { |
| "negative": { |
| "negative": 249, |
| "neutral": 47, |
| "positive": 4 |
| }, |
| "neutral": { |
| "negative": 73, |
| "neutral": 172, |
| "positive": 55 |
| }, |
| "positive": { |
| "negative": 10, |
| "neutral": 58, |
| "positive": 232 |
| } |
| } |
| }, |
| "amazon_fr": { |
| "n": 900, |
| "acc": 0.7266666666666667, |
| "macro_f1": 0.7276862376577626, |
| "conf": { |
| "negative": { |
| "negative": 241, |
| "neutral": 55, |
| "positive": 4 |
| }, |
| "neutral": { |
| "negative": 74, |
| "neutral": 188, |
| "positive": 38 |
| }, |
| "positive": { |
| "negative": 11, |
| "neutral": 64, |
| "positive": 225 |
| } |
| } |
| }, |
| "amazon_ja": { |
| "n": 900, |
| "acc": 0.6988888888888889, |
| "macro_f1": 0.7033423756574392, |
| "conf": { |
| "negative": { |
| "negative": 220, |
| "neutral": 78, |
| "positive": 2 |
| }, |
| "neutral": { |
| "negative": 68, |
| "neutral": 190, |
| "positive": 42 |
| }, |
| "positive": { |
| "negative": 5, |
| "neutral": 76, |
| "positive": 219 |
| } |
| } |
| }, |
| "amazon_zh": { |
| "n": 900, |
| "acc": 0.6188888888888889, |
| "macro_f1": 0.6130977797083769, |
| "conf": { |
| "negative": { |
| "negative": 256, |
| "neutral": 34, |
| "positive": 10 |
| }, |
| "neutral": { |
| "negative": 135, |
| "neutral": 142, |
| "positive": 23 |
| }, |
| "positive": { |
| "negative": 37, |
| "neutral": 104, |
| "positive": 159 |
| } |
| } |
| }, |
| "mteb_ara": { |
| "n": 600, |
| "acc": 0.8533333333333334, |
| "macro_f1": 0.853201214426317, |
| "conf": { |
| "negative": { |
| "negative": 247, |
| "positive": 53 |
| }, |
| "positive": { |
| "negative": 35, |
| "positive": 265 |
| } |
| } |
| }, |
| "mteb_bam": { |
| "n": 480, |
| "acc": 0.6041666666666666, |
| "macro_f1": 0.5768295625382802, |
| "conf": { |
| "negative": { |
| "negative": 84, |
| "positive": 96 |
| }, |
| "positive": { |
| "negative": 94, |
| "positive": 206 |
| } |
| } |
| }, |
| "mteb_bul": { |
| "n": 600, |
| "acc": 0.8933333333333333, |
| "macro_f1": 0.8930290604385809, |
| "conf": { |
| "negative": { |
| "negative": 252, |
| "positive": 48 |
| }, |
| "positive": { |
| "negative": 16, |
| "positive": 284 |
| } |
| } |
| }, |
| "mteb_cmn": { |
| "n": 600, |
| "acc": 0.9266666666666666, |
| "macro_f1": 0.9265066144047036, |
| "conf": { |
| "negative": { |
| "negative": 264, |
| "positive": 36 |
| }, |
| "positive": { |
| "negative": 8, |
| "positive": 292 |
| } |
| } |
| }, |
| "mteb_cym": { |
| "n": 600, |
| "acc": 0.815, |
| "macro_f1": 0.8144386769979186, |
| "conf": { |
| "negative": { |
| "negative": 228, |
| "positive": 72 |
| }, |
| "positive": { |
| "negative": 39, |
| "positive": 261 |
| } |
| } |
| }, |
| "mteb_deu": { |
| "n": 513, |
| "acc": 0.8888888888888888, |
| "macro_f1": 0.8848566467023425, |
| "conf": { |
| "negative": { |
| "negative": 276, |
| "positive": 24 |
| }, |
| "positive": { |
| "negative": 33, |
| "positive": 180 |
| } |
| } |
| }, |
| "mteb_dza": { |
| "n": 92, |
| "acc": 0.9347826086956522, |
| "macro_f1": 0.9270227392913801, |
| "conf": { |
| "negative": { |
| "negative": 28, |
| "positive": 5 |
| }, |
| "positive": { |
| "negative": 1, |
| "positive": 58 |
| } |
| } |
| }, |
| "mteb_ell": { |
| "n": 600, |
| "acc": 0.86, |
| "macro_f1": 0.86, |
| "conf": { |
| "negative": { |
| "negative": 258, |
| "positive": 42 |
| }, |
| "positive": { |
| "negative": 42, |
| "positive": 258 |
| } |
| } |
| }, |
| "mteb_eng": { |
| "n": 600, |
| "acc": 0.8933333333333333, |
| "macro_f1": 0.8930290604385809, |
| "conf": { |
| "negative": { |
| "negative": 252, |
| "positive": 48 |
| }, |
| "positive": { |
| "negative": 16, |
| "positive": 284 |
| } |
| } |
| }, |
| "mteb_eus": { |
| "n": 227, |
| "acc": 0.9251101321585903, |
| "macro_f1": 0.8511705040688033, |
| "conf": { |
| "negative": { |
| "negative": 25, |
| "positive": 10 |
| }, |
| "positive": { |
| "negative": 7, |
| "positive": 185 |
| } |
| } |
| }, |
| "mteb_fas": { |
| "n": 600, |
| "acc": 0.8066666666666666, |
| "macro_f1": 0.8042986807031751, |
| "conf": { |
| "negative": { |
| "negative": 275, |
| "positive": 25 |
| }, |
| "positive": { |
| "negative": 91, |
| "positive": 209 |
| } |
| } |
| }, |
| "mteb_fin": { |
| "n": 600, |
| "acc": 0.88, |
| "macro_f1": 0.8797380962986059, |
| "conf": { |
| "negative": { |
| "negative": 250, |
| "positive": 50 |
| }, |
| "positive": { |
| "negative": 22, |
| "positive": 278 |
| } |
| } |
| }, |
| "mteb_heb": { |
| "n": 600, |
| "acc": 0.8333333333333334, |
| "macro_f1": 0.8333314814609052, |
| "conf": { |
| "negative": { |
| "negative": 251, |
| "positive": 49 |
| }, |
| "positive": { |
| "negative": 51, |
| "positive": 249 |
| } |
| } |
| }, |
| "mteb_hrv": { |
| "n": 396, |
| "acc": 0.9570707070707071, |
| "macro_f1": 0.9425670775924583, |
| "conf": { |
| "negative": { |
| "negative": 90, |
| "positive": 6 |
| }, |
| "positive": { |
| "negative": 11, |
| "positive": 289 |
| } |
| } |
| }, |
| "mteb_ind": { |
| "n": 600, |
| "acc": 0.945, |
| "macro_f1": 0.9449815076734125, |
| "conf": { |
| "negative": { |
| "negative": 278, |
| "positive": 22 |
| }, |
| "positive": { |
| "negative": 11, |
| "positive": 289 |
| } |
| } |
| }, |
| "mteb_jpn": { |
| "n": 600, |
| "acc": 0.9333333333333333, |
| "macro_f1": 0.9333266659999333, |
| "conf": { |
| "negative": { |
| "negative": 277, |
| "positive": 23 |
| }, |
| "positive": { |
| "negative": 17, |
| "positive": 283 |
| } |
| } |
| }, |
| "mteb_kor": { |
| "n": 600, |
| "acc": 0.8066666666666666, |
| "macro_f1": 0.8064925099255997, |
| "conf": { |
| "negative": { |
| "negative": 233, |
| "positive": 67 |
| }, |
| "positive": { |
| "negative": 49, |
| "positive": 251 |
| } |
| } |
| }, |
| "mteb_mlt": { |
| "n": 171, |
| "acc": 0.8128654970760234, |
| "macro_f1": 0.7875776397515528, |
| "conf": { |
| "negative": { |
| "negative": 99, |
| "positive": 12 |
| }, |
| "positive": { |
| "negative": 20, |
| "positive": 40 |
| } |
| } |
| }, |
| "mteb_nor": { |
| "n": 417, |
| "acc": 0.86810551558753, |
| "macro_f1": 0.8379025931344486, |
| "conf": { |
| "negative": { |
| "negative": 91, |
| "positive": 27 |
| }, |
| "positive": { |
| "negative": 28, |
| "positive": 271 |
| } |
| } |
| }, |
| "mteb_pol": { |
| "n": 480, |
| "acc": 0.9854166666666667, |
| "macro_f1": 0.9851610424367688, |
| "conf": { |
| "negative": { |
| "negative": 268, |
| "positive": 3 |
| }, |
| "positive": { |
| "negative": 4, |
| "positive": 205 |
| } |
| } |
| }, |
| "mteb_rus": { |
| "n": 585, |
| "acc": 0.8940170940170941, |
| "macro_f1": 0.893927518599972, |
| "conf": { |
| "negative": { |
| "negative": 253, |
| "positive": 32 |
| }, |
| "positive": { |
| "negative": 30, |
| "positive": 270 |
| } |
| } |
| }, |
| "mteb_slk": { |
| "n": 428, |
| "acc": 0.9532710280373832, |
| "macro_f1": 0.9442708333333334, |
| "conf": { |
| "negative": { |
| "negative": 118, |
| "positive": 10 |
| }, |
| "positive": { |
| "negative": 10, |
| "positive": 290 |
| } |
| } |
| }, |
| "mteb_spa": { |
| "n": 296, |
| "acc": 0.9695945945945946, |
| "macro_f1": 0.9454176654988014, |
| "conf": { |
| "negative": { |
| "negative": 45, |
| "positive": 7 |
| }, |
| "positive": { |
| "negative": 2, |
| "positive": 242 |
| } |
| } |
| }, |
| "mteb_tha": { |
| "n": 600, |
| "acc": 0.775, |
| "macro_f1": 0.7747240369452579, |
| "conf": { |
| "negative": { |
| "negative": 222, |
| "positive": 78 |
| }, |
| "positive": { |
| "negative": 57, |
| "positive": 243 |
| } |
| } |
| }, |
| "mteb_tur": { |
| "n": 211, |
| "acc": 0.9004739336492891, |
| "macro_f1": 0.895042281545349, |
| "conf": { |
| "negative": { |
| "negative": 71, |
| "positive": 15 |
| }, |
| "positive": { |
| "negative": 6, |
| "positive": 119 |
| } |
| } |
| }, |
| "mteb_uig": { |
| "n": 400, |
| "acc": 0.7775, |
| "macro_f1": 0.6939450992529166, |
| "conf": { |
| "negative": { |
| "negative": 51, |
| "positive": 49 |
| }, |
| "positive": { |
| "negative": 40, |
| "positive": 260 |
| } |
| } |
| }, |
| "mteb_urd": { |
| "n": 294, |
| "acc": 0.782312925170068, |
| "macro_f1": 0.7797030862173934, |
| "conf": { |
| "negative": { |
| "negative": 131, |
| "positive": 20 |
| }, |
| "positive": { |
| "negative": 44, |
| "positive": 99 |
| } |
| } |
| }, |
| "mteb_vie": { |
| "n": 600, |
| "acc": 0.86, |
| "macro_f1": 0.8599937775012223, |
| "conf": { |
| "negative": { |
| "negative": 260, |
| "positive": 40 |
| }, |
| "positive": { |
| "negative": 44, |
| "positive": 256 |
| } |
| } |
| }, |
| "mteb_zho": { |
| "n": 600, |
| "acc": 0.845, |
| "macro_f1": 0.844947885261435, |
| "conf": { |
| "negative": { |
| "negative": 259, |
| "positive": 41 |
| }, |
| "positive": { |
| "negative": 52, |
| "positive": 248 |
| } |
| } |
| }, |
| "tweets_ar": { |
| "n": 870, |
| "acc": 0.6517241379310345, |
| "macro_f1": 0.6548711816568712, |
| "conf": { |
| "negative": { |
| "negative": 166, |
| "neutral": 99, |
| "positive": 25 |
| }, |
| "neutral": { |
| "negative": 40, |
| "neutral": 209, |
| "positive": 41 |
| }, |
| "positive": { |
| "negative": 14, |
| "neutral": 84, |
| "positive": 192 |
| } |
| } |
| }, |
| "tweets_en": { |
| "n": 870, |
| "acc": 0.7218390804597701, |
| "macro_f1": 0.7215787832041262, |
| "conf": { |
| "negative": { |
| "negative": 237, |
| "neutral": 48, |
| "positive": 5 |
| }, |
| "neutral": { |
| "negative": 82, |
| "neutral": 174, |
| "positive": 34 |
| }, |
| "positive": { |
| "negative": 17, |
| "neutral": 56, |
| "positive": 217 |
| } |
| } |
| }, |
| "tweets_fr": { |
| "n": 870, |
| "acc": 0.6022988505747127, |
| "macro_f1": 0.5943425281501407, |
| "conf": { |
| "negative": { |
| "negative": 193, |
| "neutral": 86, |
| "positive": 11 |
| }, |
| "neutral": { |
| "negative": 25, |
| "neutral": 227, |
| "positive": 38 |
| }, |
| "positive": { |
| "negative": 34, |
| "neutral": 152, |
| "positive": 104 |
| } |
| } |
| }, |
| "tweets_ge": { |
| "n": 870, |
| "acc": 0.6942528735632184, |
| "macro_f1": 0.6957339841093, |
| "conf": { |
| "negative": { |
| "negative": 203, |
| "neutral": 69, |
| "positive": 18 |
| }, |
| "neutral": { |
| "negative": 47, |
| "neutral": 194, |
| "positive": 49 |
| }, |
| "positive": { |
| "negative": 27, |
| "neutral": 56, |
| "positive": 207 |
| } |
| } |
| }, |
| "tweets_hi": { |
| "n": 870, |
| "acc": 0.5885057471264368, |
| "macro_f1": 0.5898121981606008, |
| "conf": { |
| "negative": { |
| "negative": 157, |
| "neutral": 94, |
| "positive": 39 |
| }, |
| "neutral": { |
| "negative": 55, |
| "neutral": 183, |
| "positive": 52 |
| }, |
| "positive": { |
| "negative": 37, |
| "neutral": 81, |
| "positive": 172 |
| } |
| } |
| }, |
| "tweets_it": { |
| "n": 870, |
| "acc": 0.7241379310344828, |
| "macro_f1": 0.724224070243718, |
| "conf": { |
| "negative": { |
| "negative": 203, |
| "neutral": 57, |
| "positive": 30 |
| }, |
| "neutral": { |
| "negative": 26, |
| "neutral": 193, |
| "positive": 71 |
| }, |
| "positive": { |
| "negative": 18, |
| "neutral": 38, |
| "positive": 234 |
| } |
| } |
| }, |
| "tweets_po": { |
| "n": 870, |
| "acc": 0.6367816091954023, |
| "macro_f1": 0.6269933992293842, |
| "conf": { |
| "negative": { |
| "negative": 171, |
| "neutral": 44, |
| "positive": 75 |
| }, |
| "neutral": { |
| "negative": 45, |
| "neutral": 129, |
| "positive": 116 |
| }, |
| "positive": { |
| "negative": 13, |
| "neutral": 23, |
| "positive": 254 |
| } |
| } |
| }, |
| "tweets_sp": { |
| "n": 870, |
| "acc": 0.674712643678161, |
| "macro_f1": 0.6691392240454653, |
| "conf": { |
| "negative": { |
| "negative": 208, |
| "neutral": 51, |
| "positive": 31 |
| }, |
| "neutral": { |
| "negative": 61, |
| "neutral": 145, |
| "positive": 84 |
| }, |
| "positive": { |
| "negative": 15, |
| "neutral": 41, |
| "positive": 234 |
| } |
| } |
| }, |
| "_tweets_mean_f1": 0.6595869210999508, |
| "_amazon_mean_f1": 0.7028148043530821, |
| "_mteb_mean_f1": 0.8574977089117052 |
| } |
| } |
