Gaa na ọdịnaya
Mụta
Akụkọ
Ngwaọrụ
Ọrụ
Ebumnuche
Chọọ
⌘K
English
Nye onyinye
NchNhr
Bido ebe a
Malite mmụta
Mụta
Gaa na Mụta
Agụmakwụkwọ
Ntuziaka
Onye nkuzi AI
Ọbá akwụkwọ ngwa ngwa
Ule
Asambodo
Nkọwa okwu
Akụkọ
Gaa na Akụkọ
Akụkọ AI kacha ọhụrụ
Ndị na-enyocha isiokwu
Nyocha & nhazi data
Blog
Ụkpụrụ nbipụta
Mmezi
Ngwaọrụ
Gaa na Ngwaọrụ
Akwụkwọ ndekọ aha
Ndepụta kacha mma
Tụlee ngwá ọrụ
Ihe mgbako ego
Nnụcha ngwa ngwa
Nyefee ngwaọrụ AI
Ọrụ
Gaa na Ọrụ
Chọgharịa ọrụ AI
Bipute ọrụ
Onye nkwado AIU
Ebumnuche
Gaa na Ebumnuche
Ebumnuche
Mmetụta & stats
Ndị ode akwụkwọ
Ebe enyemaka
Kedu ihe ọhụrụ
Nkwado
Nye onyinye
Ụlọ
/
Nkọwa okwu
/
HumanEval
Okwu nkọwapụta AI
Gịnị bụ
HumanEval
?
Nkọwa
Ihe nrịbama nke nsogbu mmemme Python ejiri iji tụọ izi ezi koodu-ọgbọ site na ule otu.
Okwu ndị metụtara
Benchmark
Nnwale ahaziri ahazi ma ọ bụ dataset ejiri tụọ na atụnyere arụmọrụ nlereanya.
GSM8K
Ihe nrịbama nke nsogbu okwu mgbakọ na mwepụ klas-ụlọ akwụkwọ ejiri iji nyochaa ntụzịaka nzọụkwụ site na nzọụkwụ n'ụdị asụsụ.
Ntọala nyocha
Ihe ndekọ data ejidere ejiri iji tụọ ịdịmma nlereanya mgbe ọzụzụ gasịrị.
Kọmpụta oge ule
Mgbakọ inference agbakwunyere na-eji n'oge ọgbọ nzaghachi iji melite ogo ma ọ bụ echiche.
gafere @k
Usoro nyocha koodu na-atụ ohere na opekata mpe otu n'ime k emepụtara na-agafe ule.
Ọchịchị AI
Atumatu, ụkpụrụ, na usoro nleba anya nke na-eduzi otu esi emepụta AI na iji ya na ọha mmadụ.
Hụkwa
MMLU
Factuality
LLM-as-Judge
Citations
Bi-Encoder
Watermarking
Cross-Encoder
Mid-training
Previous
MMLU
Next
GSM8K
Chọgharịa akwụkwọ nkọwa AI zuru ezu
Nyochaa ntuziaka AI niile efu