| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Spec-Bench | FR-Spec | MT Score195.6 | 48 | 2d ago | |
| DPR | RASD(PLD) | SR2.49 | 12 | 3d ago | |
| Qasper | RASD(PLD) | SR1.66 | 12 | 3d ago | |
| MultiFieldQA | RASD(PLD) | Speculative Rate (SR)2.1 | 12 | 3d ago | |
| CNN/Daily Mail | RASD(PLD) | SR2.31 | 12 | 3d ago | |
| HumanEval | RASD(PLD) | Speculative Rate (SR)3 | 12 | 3d ago | |
| ShareGPT Llama-3.1-8B 1.0 (test) | Eagle_LoRA_ReLU | MT-Bench Score3.2124 | 10 | 3d ago | |
| LongVideoBench ~15k visual tokens | SpecVLM | Tau (τ)3.82 | 8 | 3d ago | |
| MVBench | Sparrow | Tau (τ)3.87 | 8 | 3d ago | |
| VideoDetailCaption ~17k visual tokens | SpecVLM | Tau (τ)3.91 | 8 | 3d ago | |
| General LLM Evaluation (test) | DEER | Max Accepted Token Length32 | 8 | 3d ago | |
| Fineweb-edu distillation 8B to 300M | Random Sampling KD | Spec. Accept %62 | 7 | 3d ago | |
| Fineweb-edu 1.0 (test) | Random Sampling KD (Ours 12+) | Speculative Accept Rate0.735 | 6 | 3d ago | |
| Spec-Bench OLMo 2 7B | EAGLE-3 + SpecVocab | Conversation Score5.12 | 5 | 2d ago | |
| OOD | TABEDMTCP | Block Efficiency2.13 | 5 | 3d ago | |
| Benchmark Second Turn | TABEDMTCP | Block Efficiency2.32 | 5 | 3d ago | |
| Benchmark First Turn | TABEDMTCP | Block Efficiency2.32 | 5 | 3d ago | |
| Pre-training dataset | Speculative Accept %0.658 | 3 | 3d ago | ||
| gsm8k | GSD | Acceptance Rate83.6 | 2 | 3d ago | |
| WMT en-de 14 | GSD | Acceptance Rate0.848 | 2 | 3d ago | |
| Alpaca | GSD | Acceptance Rate79.3 | 2 | 3d ago |
