Mga BenchmarkGPT-oss-120BUrdu (Pakistan) mga gawain

GPT-oss-120B

8 mga gawain

Ang bawat row sa ibaba ay isang benchmark na gawain na sinuri ang modelong ito. Ina-average ng column na Score ang bawat metric na iniuulat ng gawain (katumpakan, F1, exact-match, atbp.). I-click ang isang row para i-browse ang mga indibidwal na tanong at mga tugon ng modelo.

Average

47.1

Marka	Wika	Gawain	Mga sukatan
87.1	Urdu (Pakistan)	urdu_uquad urdu qa llm_judge_score: 87.1sample_len: 139.0	llm_judge_score: 87.1sample_len: 139.0
66.9	Urdu (Pakistan)	urdu_freshqa urdu qa llm_judge_score: 66.9sample_len: 323.0	llm_judge_score: 66.9sample_len: 323.0
45.9	Urdu (Pakistan)	urdu_facttool_qa urdu claim f1_macro: 45.9sample_len: 160.0	f1_macro: 45.9sample_len: 160.0
45.9	Urdu (Pakistan)	urdu_factcheckbench urdu claim f1_macro: 45.9sample_len: 387.0	f1_macro: 45.9sample_len: 387.0
44.3	Urdu (Pakistan)	urdu_bingcheck urdu claim f1_macro: 44.3sample_len: 102.0	f1_macro: 44.3sample_len: 102.0
37.6	Urdu (Pakistan)	urdu_fake_news urdu classification f1_macro: 37.6sample_len: 300.0	f1_macro: 37.6sample_len: 300.0
28.6	Urdu (Pakistan)	urdu_emotion_class urdu classification f1_macro: 28.6sample_len: 200.0	f1_macro: 28.6sample_len: 200.0
20.5	Urdu (Pakistan)	urdu_simpleqa urdu qa llm_judge_score: 20.5sample_len: 200.0	llm_judge_score: 20.5sample_len: 200.0