Generative Question Answering on FatwaQA
67AccuracyGemini-3-Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini-3-ProEvaluation Protocol=LLM-as-a-judge2026.03 | 67 | |
| Fanar-SadiqEvaluation Protocol=LLM-as-a-judge2026.03 | 65.1 | |
| GPT-5Evaluation Protocol=LLM-as-a-judge2026.03 | 63.6 | |
| Gemini-3-FlashEvaluation Protocol=LLM-as-a-judge2026.03 | 54.6 | |
| FanarEvaluation Protocol=LLM-as-a-judge, Parameters=2-27B2026.03 | 44.5 | |
| GPT-4.1Evaluation Protocol=LLM-as-a-judge2026.03 | 32.3 | |
| ALLaMEvaluation Protocol=LLM-as-a-judge, Parameters=7B2026.03 | 31.5 |