Utility Evaluation on SLIMORCA (test)
68.85ScoreTOSS-Pro
Evaluation results
| Method | Links | |
|---|---|---|
| TOSS-ProModel=Llama-3-8B-Instruct2026.03 | 68.85 | |
| TOSSModel=Llama-3-8B-Instruct2026.03 | 68.37 | |
| TOSS-ProModel=Llama-2-7B-Chat-hf2026.03 | 60.73 | |
| TOSSModel=Llama-3.2-3B-Instruct2026.03 | 58.78 | |
| SEALModel=Llama-3-8B-Instruct2026.03 | 57.41 | |
| TOSSModel=Llama-2-7B-Chat-hf2026.03 | 57.29 | |
| TOSSModel=Llama-3.2-1B-Instruct2026.03 | 55.34 | |
| DSIRModel=Llama-3-8B-Instruct2026.03 | 53.81 | |
| SafeInstrModel=Llama-2-7B-Chat-hf2026.03 | 53.1 | |
| RandomModel=Llama-2-7B-Chat-hf2026.03 | 52.74 | |
| SEALModel=Llama-2-7B-Chat-hf2026.03 | 52.51 | |
| DSIRModel=Llama-2-7B-Chat-hf2026.03 | 52.03 | |
| SEALModel=Llama-3.2-1B-Instruct2026.03 | 51.66 | |
| SEALModel=Llama-3.2-3B-Instruct2026.03 | 50.83 | |
| SafeInstrModel=Llama-3.2-1B-Instruct2026.03 | 50.59 | |
| SafeInstrModel=Llama-3-8B-Instruct2026.03 | 50.47 | |
| SafeInstrModel=Llama-3.2-3B-Instruct2026.03 | 50.47 | |
| Standard SFTModel=Llama-3-8B-Instruct2026.03 | 50 | |
| Standard SFTModel=Llama-2-7B-Chat-hf2026.03 | 50 | |
| Standard SFTModel=Llama-3.2-1B-Instruct2026.03 | 50 | |
| Standard SFTModel=Llama-3.2-3B-Instruct2026.03 | 50 | |
| DSIRModel=Llama-3.2-3B-Instruct2026.03 | 48.81 | |
| RandomModel=Llama-3-8B-Instruct2026.03 | 47.97 | |
| DSIRModel=Llama-3.2-1B-Instruct2026.03 | 47.62 |