Legal Knowledge Assessment on Laws
97.4Accuracysabia-4
Evaluation Results
| Method | Links | |
|---|---|---|
| sabia-42026.03 | 97.4 | |
| Gemini-3 ProModel variant=high2026.03 | 88.6 | |
| gpt-5.2Model variant=high2026.03 | 86.3 | |
| sabiazinho-4Price Range=cost-effective2026.03 | 85 | |
| gpt-5.2Model variant=instant2026.03 | 84 | |
| gpt-4.12026.03 | 80.8 | |
| sabia-3.12026.03 | 77.8 | |
| Gemini-3 ProModel variant=low2026.03 | 74.9 | |
| gemini-2.5-flash-litePrice Range=cost-effective2026.03 | 72.1 | |
| gpt-5-miniPrice Range=cost-effective2026.03 | 68.2 | |
| deepseekModel variant=v3.22026.03 | 67.3 | |
| Qwen3Model variant=235b2026.03 | 65.9 | |
| kimi-k2Model variant=thinking2026.03 | 59.1 | |
| gpt-4.1-miniPrice Range=cost-effective2026.03 | 57 | |
| gpt-oss-120bPrice Range=cost-effective2026.03 | 52.3 |