Machine Translation on WMT literary translation (zh→en) 24
94.62SEGALE Comet ScoreLlama-3.1_TMPC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Llama-3.1_TMPCTest-Time=✓2025.02 | 94.62 | 0 | |
| GPT-4o 2024-08-06Test-Time=-2025.02 | 94.58 | 0.1 | |
| Qwen-2.5 (14B)Test-Time=-2025.02 | 94.43 | 0.18 | |
| Llama-3.1_SFTTest-Time=×2025.02 | 93.54 | 0.34 | |
| Llama-3.1_SimPOTest-Time=×2025.02 | 91.74 | 1.66 | |
| Llama-3.1_Best-of-60Test-Time=✓2025.02 | 90.97 | 3.58 | |
| Llama-3.1_DPOTest-Time=×2025.02 | 90.23 | 1.33 | |
| Llama-3.1_TPOTest-Time=✓2025.02 | 88.81 | 5.63 | |
| Llama-3.1_RE-ControlTest-Time=✓2025.02 | 86.39 | 7.06 | |
| Llama-3.1 (8B)Test-Time=×2025.02 | 84.36 | 10.47 | |
| Llama-3.1_ARGSTest-Time=✓2025.02 | 63.99 | 31.53 | |
| Llama-3.1_GenARMTest-Time=✓2025.02 | 61.18 | 34.73 | |
| Llama-3.1_RAINTest-Time=✓2025.02 | 58.52 | 37.18 |