Multi-turn Conversation on MT-Bench (SR and Tau)
5.23SRGTO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GTOModel=Vicuna-1.3 13B, Temperature=02025.09 | 5.23 | 7.01 | |
| EAGLE-3Model=Vicuna-1.3 13B, Temperature=02025.09 | 4.84 | 6.59 | |
| EAGLE-3Model=Vicuna-1.3 13B, Temperature=12025.09 | 4.1 | 5.71 | |
| GTOModel=Vicuna-1.3 13B, Temperature=12025.09 | 4.1 | 5.71 | |
| EAGLE2Model=Vicuna-1.3 13B, Temperature=12025.09 | 4.03 | 5.64 | |
| GTOModel=LLaMA-3.3 Instruct 70B, Temperature=02025.09 | 3.97 | 5.56 | |
| GTOModel=LLaMA-3.3 Instruct 70B, Temperature=12025.09 | 3.9 | 5.34 | |
| EAGLE2Model=Vicuna-1.3 13B, Temperature=02025.09 | 3.79 | 4.78 | |
| EAGLE-3Model=LLaMA-3.3 Instruct 70B, Temperature=02025.09 | 3.78 | 5.4 | |
| EAGLE-3Model=LLaMA-3.3 Instruct 70B, Temperature=12025.09 | 3.68 | 5.18 | |
| GTOModel=DeepSeek-R1 Distill-LLaMA 8B, Temperature=02025.09 | 3.49 | 5.6 | |
| EAGLEModel=Vicuna-1.3 13B, Temperature=12025.09 | 3.47 | 4.33 | |
| GTOModel=LLaMA-3.1 Instruct 8B, Temperature=02025.09 | 3.44 | 6.15 | |
| EAGLE-3Model=DeepSeek-R1 Distill-LLaMA 8B, Temperature=02025.09 | 3.34 | 5.32 | |
| EAGLE-3Model=LLaMA-3.1 Instruct 8B, Temperature=02025.09 | 3.27 | 5.77 | |
| GRIFFINModel=LLaMA-3.1 Instruct 8B, Temperature=02025.09 | 2.95 | 4.68 | |
| EAGLEModel=Vicuna-1.3 13B, Temperature=02025.09 | 2.81 | 3.67 | |
| GTOModel=DeepSeek-R1 Distill-LLaMA 8B, Temperature=12025.09 | 2.76 | 4.59 | |
| GRIFFINModel=DeepSeek-R1 Distill-LLaMA 8B, Temperature=02025.09 | 2.71 | 4.24 | |
| EAGLE-3Model=DeepSeek-R1 Distill-LLaMA 8B, Temperature=12025.09 | 2.71 | 4.54 | |
| HydraModel=Vicuna-1.3 13B, Temperature=02025.09 | 2.57 | 3.25 | |
| EAGLE-2Model=LLaMA-3.1 Instruct 8B, Temperature=02025.09 | 2.52 | 4.02 | |
| GTOModel=LLaMA-3.1 Instruct 8B, Temperature=12025.09 | 2.49 | 4.7 | |
| GTOModel=Qwen-3 8B, Temperature=02025.09 | 2.49 | 4.84 | |
| GRIFFINModel=DeepSeek-R1 Distill-LLaMA 8B, Temperature=12025.09 | 2.38 | 3.93 | |
| EAGLE-3Model=LLaMA-3.1 Instruct 8B, Temperature=12025.09 | 2.37 | 4.51 | |
| EAGLE-3Model=Qwen-3 8B, Temperature=02025.09 | 2.37 | 4.53 | |
| GRIFFINModel=LLaMA-3.1 Instruct 8B, Temperature=12025.09 | 2.29 | 3.9 | |
| GTOModel=Qwen-3 8B, Temperature=12025.09 | 2.29 | 4.37 | |
| EAGLE-3Model=Qwen-3 8B, Temperature=12025.09 | 2.24 | 4.23 | |
| HydraModel=Vicuna-1.3 13B, Temperature=12025.09 | 2.14 | 3.06 | |
| EAGLE-2Model=LLaMA-3.1 Instruct 8B, Temperature=12025.09 | 2.04 | 3.13 | |
| MedusaModel=Vicuna-1.3 13B, Temperature=02025.09 | 1.99 | 2.48 | |
| SPSModel=Vicuna-1.3 13B, Temperature=02025.09 | 1.91 | 2.24 | |
| EAGLEModel=LLaMA-3.1 Instruct 8B, Temperature=02025.09 | 1.73 | 2.97 | |
| EAGLEModel=LLaMA-3.1 Instruct 8B, Temperature=12025.09 | 1.62 | 2.39 | |
| LookaheadModel=LLaMA-3.1 Instruct 8B, Temperature=02025.09 | 1.61 | 1.67 | |
| SPSModel=Vicuna-1.3 13B, Temperature=12025.09 | 1.59 | 1.81 | |
| LookaheadModel=LLaMA-3.3 Instruct 70B, Temperature=02025.09 | 1.58 | 1.66 | |
| PLDModel=LLaMA-3.1 Instruct 8B, Temperature=02025.09 | 1.53 | 1.61 | |
| LookaheadModel=DeepSeek-R1 Distill-LLaMA 8B, Temperature=02025.09 | 1.52 | 1.61 | |
| PLDModel=LLaMA-3.3 Instruct 70B, Temperature=02025.09 | 1.43 | 1.51 | |
| PLDModel=DeepSeek-R1 Distill-LLaMA 8B, Temperature=02025.09 | 1.34 | 1.42 |