ModelChorusModelChorus
ÌpèníjàÌjíròròTábìlì OlóríFàIdanwoÌtàn
Bí ó ṣe ń ṣiṣẹAPIÀwọn Òfin IṣẹÌlànà Àṣírí

Ẹtọ akọọlẹ 2026 MeetKai Inc.

Idanwo/Functionary Swahili Mini/Gbogbo iṣẹ́

Functionary Swahili Mini

iṣẹ́ 22

Ẹsẹ̀ ọ̀rọ̀ kọ̀ọ̀kan tó wà nísàlẹ̀ jẹ́ iṣẹ́ ìdánwò ẹyọ kan tí a fi àwòkọ́ṣe yìí dán wò. Òpó Àmì-ìwọ̀n máa ń ka àpapọ̀ gbogbo ìwọ̀n tí iṣẹ́ náà ròyìn (deedee, F1, ìbámu pípé, abbl.). Tẹ ẹsẹ̀ ọ̀rọ̀ kan láti ṣàwárí àwọn ìbéèrè ẹyọ àti àwọn ìdáhùn àwòkọ́ṣe.

Àpapọ̀
62.2
Iye-àmìÈdèIṣẹ́Àwọn ìwọ̀n
95.9Ukrainian (Ukraine)
ukrainian_polywrite
ukrainian open generation
open_quality_score: 95.9sample_len: 154.0
open_quality_score: 95.9sample_len: 154.0
88.7French (France)
french_sib200
french classification
f1_macro: 88.7sample_len: 204.0
f1_macro: 88.7sample_len: 204.0
87.8Ukrainian (Ukraine)
ukrainian_sib200
ukrainian classification
f1_macro: 87.8sample_len: 204.0
f1_macro: 87.8sample_len: 204.0
87.7Portuguese (Portugal)
portuguese_hatebr
portuguese classification
f1_macro: 87.7sample_len: 1400.0
f1_macro: 87.7sample_len: 1400.0
86.8Arabic (Saudi Arabia)
arabic_sib200
arabic classification
f1_macro: 86.8sample_len: 204.0
f1_macro: 86.8sample_len: 204.0
85.9Swahili (Tanzania)
swahili_sib200
swahili classification
f1_macro: 85.9sample_len: 204.0
f1_macro: 85.9sample_len: 204.0
85.4Albanian (Albania)
albanian_sib200
albanian classification
f1_macro: 85.4sample_len: 204.0
f1_macro: 85.4sample_len: 204.0
83.8Urdu (Pakistan)
urdu_facttool_qa
urdu claim
f1_macro: 83.8sample_len: 160.0
f1_macro: 83.8sample_len: 160.0
82.6Hausa (Nigeria)
hausa_sib200
hausa classification
f1_macro: 82.6sample_len: 204.0
f1_macro: 82.6sample_len: 204.0
75.0Urdu (Pakistan)
urdu_factcheckbench
urdu claim
f1_macro: 75.0sample_len: 387.0
f1_macro: 75.0sample_len: 387.0
73.9Urdu (Pakistan)
urdu_bingcheck
urdu claim
f1_macro: 73.9sample_len: 102.0
f1_macro: 73.9sample_len: 102.0
73.6French (France)
french_mgsm
french math
exact_match: 73.6sample_len: 250.0
exact_match: 73.6sample_len: 250.0
72.8Urdu (Pakistan)
urdu_fake_news
urdu classification
f1_macro: 72.8sample_len: 300.0
f1_macro: 72.8sample_len: 300.0
70.5Portuguese (Portugal)
portuguese_tweetsentbr
portuguese classification
f1_macro: 70.5sample_len: 2010.0
f1_macro: 70.5sample_len: 2010.0
69.8Hausa (Nigeria)
hausa_afrixnli
hausa nli
f1_macro: 69.8sample_len: 600.0
f1_macro: 69.8sample_len: 600.0
69.2Portuguese (Portugal)
portuguese_hate_speech
portuguese classification
f1_macro: 69.2sample_len: 851.0
f1_macro: 69.2sample_len: 851.0
37.7English (US)
english_mmlu_pro
english mmlu pro
exact_match: 37.7sample_len: 2100.0
exact_match: 37.7sample_len: 2100.0
30.4Urdu (Pakistan)
urdu_emotion_class
urdu classification
f1_macro: 30.4sample_len: 200.0
f1_macro: 30.4sample_len: 200.0
9.6English (US)
english_belebele
english mcq
f1_macro: 9.6sample_len: 900.0
f1_macro: 9.6sample_len: 900.0
0.5French (France)
french_fquad
french qa
exact_match: 0.5f1: 0.5sample_len: 400.0
exact_match: 0.5f1: 0.5sample_len: 400.0
0.0Arabic (Saudi Arabia)
arabic_tydiqa
arabic qa
exact_match: 0.0f1: 0.0sample_len: 921.0
exact_match: 0.0f1: 0.0sample_len: 921.0
0.0Hausa (Nigeria)
hausa_afriqa
hausa qa
exact_match: 0.0f1: 0.0sample_len: 300.0
exact_match: 0.0f1: 0.0sample_len: 300.0