ModelChorusModelChorus
Ịma akaNkataLeaderboardSụgharịaNtuleAkụkọ
Otu o si arụ ọrụAPIUsoro ỌrụIwu Nzuzo

Ikike nchekwa 2026 MeetKai Inc.

Ntule/GPT-5 Nano/Ọrụ niile

GPT-5 Nano

ọrụ 52

Ahịrị ọ bụla n'okpuru bụ otu ọrụ nyocha ụdị a nyochara. Kọlụm Akara na-ekewu atụtụ niile ọrụ ahụ na-akọ (izi ezi, F1, otu n'otu, wdg.). Pịa ahịrị iji nyochaa ajụjụ dị iche iche na nzaghachi nke ụdị.

Nkezi
68.4
AkaraAsụsụỌrụAtụtụ
92.1Ukrainian (Ukraine)
ukrainian_belebele
ukrainian mcq
f1_macro: 92.1sample_len: 900.0
f1_macro: 92.1sample_len: 900.0
91.1Portuguese (Portugal)
portuguese_hatebr
portuguese classification
f1_macro: 91.1sample_len: 1400.0
f1_macro: 91.1sample_len: 1400.0
90.4Portuguese (Portugal)
portuguese_enem
portuguese mcq
exact_match: 90.4sample_len: 1432.0
exact_match: 90.4sample_len: 1432.0
89.8French (France)
french_sib200
french classification
f1_macro: 89.8sample_len: 204.0
f1_macro: 89.8sample_len: 204.0
89.4Albanian (Albania)
albanian_belebele
albanian mcq
f1_macro: 89.4sample_len: 900.0
f1_macro: 89.4sample_len: 900.0
89.2Urdu (Pakistan)
urdu_uquad
urdu qa
llm_judge_score: 89.2sample_len: 139.0
llm_judge_score: 89.2sample_len: 139.0
89.0Albanian (Albania)
albanian_aya
albanian open generation
llm_judge_score: 89.0sample_len: 200.0
llm_judge_score: 89.0sample_len: 200.0
88.7Albanian (Albania)
albanian_sib200
albanian classification
f1_macro: 88.7sample_len: 204.0
f1_macro: 88.7sample_len: 204.0
87.4Portuguese (Portugal)
portuguese_bluex
portuguese mcq
exact_match: 87.4sample_len: 724.0
exact_match: 87.4sample_len: 724.0
87.3English (US)
english_gsm8k
english math
exact_match: 87.3sample_len: 1319.0
exact_match: 87.3sample_len: 1319.0
87.2English (US)
english_mgsm
english math
exact_match: 87.2sample_len: 250.0
exact_match: 87.2sample_len: 250.0
86.5Ukrainian (Ukraine)
ukrainian_polywrite
ukrainian open generation
open_quality_score: 86.5sample_len: 154.0
open_quality_score: 86.5sample_len: 154.0
86.3Swahili (Tanzania)
swahili_sib200
swahili classification
f1_macro: 86.3sample_len: 204.0
f1_macro: 86.3sample_len: 204.0
85.2Ukrainian (Ukraine)
ukrainian_sib200
ukrainian classification
f1_macro: 85.2sample_len: 204.0
f1_macro: 85.2sample_len: 204.0
85.1Ukrainian (Ukraine)
ukrainian_global_mmlu
ukrainian mcq
f1_macro: 85.1sample_len: 2850.0
f1_macro: 85.1sample_len: 2850.0
84.7Arabic (Saudi Arabia)
arabic_sib200
arabic classification
f1_macro: 84.7sample_len: 204.0
f1_macro: 84.7sample_len: 204.0
84.2Hausa (Nigeria)
hausa_sib200
hausa classification
f1_macro: 84.2sample_len: 204.0
f1_macro: 84.2sample_len: 204.0
82.9Albanian (Albania)
albanian_global_mmlu
albanian mcq
f1_macro: 82.9sample_len: 400.0
f1_macro: 82.9sample_len: 400.0
77.4Urdu (Pakistan)
urdu_bingcheck
urdu claim
f1_macro: 77.4sample_len: 102.0
f1_macro: 77.4sample_len: 102.0
76.8Swahili (Tanzania)
swahili_afrimgsm
swahili afrimgsm
exact_match: 76.8sample_len: 250.0
exact_match: 76.8sample_len: 250.0
75.6Albanian (Albania)
albanian_polywrite
albanian open generation
open_quality_score: 75.6sample_len: 155.0
open_quality_score: 75.6sample_len: 155.0
75.2Urdu (Pakistan)
urdu_freshqa
urdu qa
llm_judge_score: 75.2sample_len: 323.0
llm_judge_score: 75.2sample_len: 323.0
73.5Arabic (Saudi Arabia)
arabic_aratrust
arabic mcq
f1_macro: 73.5sample_len: 522.0
f1_macro: 73.5sample_len: 522.0
73.0Portuguese (Portugal)
portuguese_tweetsentbr
portuguese classification
f1_macro: 73.0sample_len: 2010.0
f1_macro: 73.0sample_len: 2010.0
69.2Ukrainian (Ukraine)
ukrainian_zno
ukrainian mcq
f1_macro: 69.2sample_len: 751.0
f1_macro: 69.2sample_len: 751.0
69.2French (France)
french_mgsm
french math
exact_match: 69.2sample_len: 250.0
exact_match: 69.2sample_len: 250.0
68.4Hausa (Nigeria)
hausa_afrixnli
hausa nli
f1_macro: 68.4sample_len: 600.0
f1_macro: 68.4sample_len: 600.0
67.7Spanish (Spain)
spanish_xquad_es
spanish xquad es
exact_match: 57.1f1: 78.4sample_len: 1190.0
exact_match: 57.1f1: 78.4sample_len: 1190.0
66.1Portuguese (Portugal)
portuguese_hate_speech
portuguese classification
f1_macro: 66.1sample_len: 851.0
f1_macro: 66.1sample_len: 851.0
65.3Urdu (Pakistan)
urdu_factcheckbench
urdu claim
f1_macro: 65.3sample_len: 387.0
f1_macro: 65.3sample_len: 387.0
65.2Swahili (Tanzania)
swahili_afrixnli
swahili nli
f1_macro: 65.2sample_len: 600.0
f1_macro: 65.2sample_len: 600.0
62.8Hausa (Nigeria)
hausa_afrimgsm
hausa afrimgsm
exact_match: 62.8sample_len: 250.0
exact_match: 62.8sample_len: 250.0
62.4Ukrainian (Ukraine)
ukrainian_squad
ukrainian qa
exact_match: 49.2f1: 75.6sample_len: 3812.0
exact_match: 49.2f1: 75.6sample_len: 3812.0
61.7Arabic (Saudi Arabia)
arabic_belebele
arabic mcq
f1_macro: 61.7sample_len: 900.0
f1_macro: 61.7sample_len: 900.0
61.6Urdu (Pakistan)
urdu_facttool_qa
urdu claim
f1_macro: 61.6sample_len: 160.0
f1_macro: 61.6sample_len: 160.0
61.6English (US)
english_mmlu_pro
english mmlu pro
exact_match: 61.6sample_len: 2100.0
exact_match: 61.6sample_len: 2100.0
61.0Spanish (Spain)
spanish_belebele
spanish mcq
f1_macro: 61.0sample_len: 900.0
f1_macro: 61.0sample_len: 900.0
59.7Portuguese (Portugal)
portuguese_oab_exams
portuguese mcq
exact_match: 59.7sample_len: 2210.0
exact_match: 59.7sample_len: 2210.0
59.2French (France)
french_fquad
french qa
exact_match: 55.3f1: 63.1sample_len: 400.0
exact_match: 55.3f1: 63.1sample_len: 400.0
57.7French (France)
french_belebele
french mcq
f1_macro: 57.7sample_len: 900.0
f1_macro: 57.7sample_len: 900.0
57.7Arabic (Saudi Arabia)
arabic_mmlu
arabic mcq
f1_macro: 57.7sample_len: 14316.0
f1_macro: 57.7sample_len: 14316.0
57.6Urdu (Pakistan)
urdu_fake_news
urdu classification
f1_macro: 57.6sample_len: 300.0
f1_macro: 57.6sample_len: 300.0
56.5Spanish (Spain)
spanish_global_mmlu
spanish mcq
f1_macro: 56.5sample_len: 400.0
f1_macro: 56.5sample_len: 400.0
52.1Hausa (Nigeria)
hausa_belebele
hausa mcq
f1_macro: 52.1sample_len: 900.0
f1_macro: 52.1sample_len: 900.0
51.8French (France)
french_mmmlu
french mcq
f1_macro: 51.8sample_len: 14042.0
f1_macro: 51.8sample_len: 14042.0
51.2English (US)
english_belebele
english mcq
f1_macro: 51.2sample_len: 900.0
f1_macro: 51.2sample_len: 900.0
40.5Arabic (Saudi Arabia)
arabic_tydiqa
arabic qa
exact_match: 35.5f1: 45.4sample_len: 921.0
exact_match: 35.5f1: 45.4sample_len: 921.0
39.3Hausa (Nigeria)
hausa_afrimmlu
hausa mcq
f1_macro: 39.3sample_len: 500.0
f1_macro: 39.3sample_len: 500.0
32.5English (US)
ifeval
ifeval
inst_level_loose_acc: 39.3inst_level_strict_acc: 38.5prompt_level_loose_acc: 26.6prompt_level_strict_acc: 25.7sample_len: 541.0
inst_level_loose_acc: 39.3inst_level_strict_acc: 38.5prompt_level_loose_acc: 26.6prompt_level_strict_acc: 25.7sample_len: 541.0
28.5Urdu (Pakistan)
urdu_emotion_class
urdu classification
f1_macro: 28.5sample_len: 200.0
f1_macro: 28.5sample_len: 200.0
23.3Hausa (Nigeria)
hausa_afriqa
hausa qa
exact_match: 22.3f1: 24.2sample_len: 300.0
exact_match: 22.3f1: 24.2sample_len: 300.0
21.0Urdu (Pakistan)
urdu_simpleqa
urdu qa
llm_judge_score: 21.0sample_len: 200.0
llm_judge_score: 21.0sample_len: 200.0