Multiple Choice Question Answering on LegalMC4 (test)
72Exact AccuracyGPT-5 (min. reasoning)
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5 (min. reasoning)Train Data=Base Model2026.01 | 72 | |
| Gemma 3 (12B)Train Data=Difficulty-Graded QA Data2026.01 | 71.2 | |
| GPT-5-mini (min. reasoning)Train Data=Base Model2026.01 | 70.9 | |
| Gemma 3 (12B)Train Data=Standard Instruction QA Data2026.01 | 66.9 | |
| Gemma 3 (12B)Train Data=Base Model2026.01 | 66.8 | |
| LLaMA 3.1 (8B)Train Data=Difficulty-Graded QA Data2026.01 | 66.1 | |
| LLaMA 3.1 (8B)Train Data=Base Model2026.01 | 60.9 | |
| LLaMA 3.1 (8B)Train Data=Standard Instruction QA Data2026.01 | 59.9 |