Classification on Human-Internal
94.14Binary AccuracyLMUNIT LLaMA3.1-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| LMUNIT LLaMA3.1-8BBase Model Architecture=LLaMA-3.1-8B2024.12 | 94.14 | |
| LMUNIT LLaMA3.1-70BBase Model Architecture=LLaMA-3.1-70B2024.12 | 93.63 | |
| LMUNIT LLaMA3.1-70B-DecomposedBase Model Architecture=LLaMA-3.1-70B, Decomposed unit tests=true2024.12 | 93.63 | |
| LMUNIT LLaMA3.1-70B-Decomposed-WeightedBase Model Architecture=LLaMA-3.1-70B, Decomposed unit tests=true, Bayesian optimization=true, Weighting Strategy=Weighted2024.12 | 93.63 | |
| Claude-3.5 Sonnet2024.12 | 84.53 | |
| GPT-4o2024.12 | 81.8 | |
| Prometheus-2-BGB-8x7B2024.12 | 78.57 | |
| Prometheus-2-8x7BBase Model Architecture=Mistral-8x7B2024.12 | 77.82 | |
| Prometheus-2-7BBase Model Architecture=Llama-2-7B2024.12 | 75.58 | |
| Llama-3-OffsetBias-8BBase Model Architecture=Llama-3-8B2024.12 | 68.15 |