Multiple Choice Question Answering on IslamTrust
95.6AccuracyGemini-3-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-ProEvaluation Protocol=Exact-match2026.03 | 95.6 | |
| GPT-5Evaluation Protocol=Exact-match2026.03 | 95.2 | |
| Gemini-3-FlashEvaluation Protocol=Exact-match2026.03 | 94.8 | |
| GPT-4.1Evaluation Protocol=Exact-match2026.03 | 94.7 | |
| Fanar-SadiqEvaluation Protocol=Exact-match2026.03 | 94.2 | |
| FanarEvaluation Protocol=Exact-match, Parameters=2-27B2026.03 | 83.2 | |
| ALLaMEvaluation Protocol=Exact-match, Parameters=7B2026.03 | 57.4 |