Judgment on Principle-based evaluation dataset
8.45G ScoreGPT-5.1
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| GPT-5.1Access Type=API-based2025.12 | 8.45 | 8.51 | 8.25 | 8.39 | 8.26 | 8.35 | |
| Claude 3.5-HaikuAccess Type=API-based2025.12 | 8.4 | 8.54 | 8.18 | 8.55 | 8.25 | 8.48 | |
| Claude 4.5-HaikuAccess Type=API-based2025.12 | 8.4 | 8.63 | 8.08 | 8.29 | 8.3 | 8.18 | |
| GPT-4.1Access Type=API-based2025.12 | 8.3 | 8.65 | 8.23 | 8.39 | 8.35 | 8.38 | |
| Qwen3-8BAccess Type=Open-source2025.12 | 8.28 | 8.38 | 8.01 | 8.32 | 8.21 | 8.28 | |
| Claude 4.5-SonnetAccess Type=API-based2025.12 | 8.23 | 8.49 | 8.06 | 8.49 | 8.39 | 8.35 | |
| Qwen3-4BAccess Type=Open-source2025.12 | 8.13 | 8.48 | 8.04 | 8.29 | 8.2 | 8.23 | |
| Qwen2.5-7BAccess Type=Open-source2025.12 | 8.11 | 8.1 | 7.77 | 8.12 | 7.81 | 7.98 | |
| GPT-5Access Type=API-based2025.12 | 8.11 | 8.35 | 7.84 | 8.2 | 8.23 | 7.98 | |
| Qwen3-1.7BAccess Type=Open-source2025.12 | 8.02 | 8.23 | 7.92 | 8.12 | 7.7 | 7.85 | |
| Llama-3.2-3BAccess Type=Open-source2025.12 | 8 | 7.94 | 7.58 | 7.85 | 7.89 | 7.85 | |
| Llama-3.1-8BAccess Type=Open-source2025.12 | 7.79 | 7.89 | 7.81 | 7.96 | 7.7 | 7.9 |