Machine Translation

Best model: tensorflow/tensor2tensor

Best model: Multilingual Transformer

Best model: HWTSC-Teacher-Sim

Best model: T5

Best model: Larger

Best model: Transformer-base

Best model: GenTranslate-7B

Best model: SeamlessM4T Large

Best model: GPT-4o (HPT)

Best model: PiNMT

Best model: BP-Transformer

Best model: PS-KD

Best model: EnViT5 + MTet

Best model: PS-KD

Best model: Seq-KD + Seq-Inter + Word-KD

Best model: Transformer base + BPE-Dropout

Best model: Transformer base + BPE-Dropout

Best model: NLLB-200

Best model: Adaptively Sparse Transformer (alpha-entmax)

Best model: ChatGPT

Best model: slone/mbart-large-51-myv-mul-v1

Best model: PENELOPIE Transformers-based NMT (EN2EL)

Best model: M_C

Best model: DynamicConv

Best model: Multi-pass backtranslated adapted transformer

Best model: Transformer trained on highly filtered data

Best model: Multi-pass backtranslated adapted transformer

Best model: Vega-MT

Best model: Vega-MT

Best model: Evolved Transformer Big

Best model: Transformer+BT (ADMIN init)

Best model: Transformer Cycle (Rev)

Best model: Bi-SimCut

Best model: C2-50k Segmentation

Best model: ByteNet

Best model: Attentional encoder-decoder + BPE

Best model: Attentional encoder-decoder + BPE

Best model: DeLighT

Best model: DeLighT

Best model: fast-noisy-channel-modeling

Best model: StrokeNet

Best model: OmniNetP

Best model: OmniNetP

Best model: OmniNetP

Best model: OmniNetP

Best model: Facebook FAIR (ensemble)