General Performance on Overall
62.05Overall ScoreUltraMix-190k
Evaluation Results
| Method | Links | |
|---|---|---|
| UltraMix-190kBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=UM-190k2025.11 | 62.05 | |
| UltraMix-187kBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=UM-187k2025.11 | 61.62 | |
| UltraMix-170kBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=UM-170k2025.11 | 60.48 | |
| TuluDPOBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=TuluDPO2025.11 | 59.56 | |
| SFTBase Model=Qwen-2.5-7B-TuluSFT, Training Mixture/Protocol=SFT2025.11 | 56.55 | |
| UltraMix-190kBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=UM-190k2025.11 | 56.04 | |
| UltraMix-187kBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=UM-187k2025.11 | 55.36 | |
| UltraMix-170kBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=UM-170k2025.11 | 54.16 | |
| TuluDPOBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=TuluDPO2025.11 | 53.96 | |
| SFTBase Model=Llama-3.1-8B-TuluSFT, Training Mixture/Protocol=SFT2025.11 | 50.09 | |
| UM-190k2025.11 | 36.57 | |
| UM-187k2025.11 | 36.17 | |
| TuluDPO2025.11 | 35.31 | |
| ORPO2025.11 | 35.13 | |
| UM-170k2025.11 | 34.78 | |
| UltraFB2025.11 | 34.05 | |
| SFT2025.11 | 34.04 | |
| HelpSteer2025.11 | 33.66 | |
| CodePref2025.11 | 32.63 |