Yehia-7B-preview: benchmark results
Navid AI's Yehia 7B preview, a 7B fine-tune of ALLaM-AI's ALLaM-7B-Instruct-preview base model. Provider: Navid AI. Released 2025-02-27. Access: Open.
Aggregate Rating 1534 ± 26, rank #659 of 1635 rated models, from 162 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Arabic LLM - Aratrust Ethics | 83.33 | Accuracy (%) | 99.1 |
| Open Arabic LLM - Aratrust Trustfulness | 82.05 | Accuracy (%) | 99.1 |
| QIMMA - AraDiCE-Culture | 81.67 | Accuracy (%, log-likelihood multiple choice) | 98.8 |
| Open Arabic LLM - Arabic MMLU Islamic Studies (Middle School) | 76.47 | Accuracy (%) | 95.1 |
| Open Arabic LLM - Arabic MMLU Islamic Studies (Primary School) | 84.88 | Accuracy (%) | 94.4 |
| QIMMA - ArabCulture | 75.47 | Accuracy (%, log-likelihood multiple choice) | 92.7 |
| QIMMA - FannOrFlop | 59.64 | F1 (%) | 92.7 |
| Open Arabic LLM - Arabic MMLU Arabic Language (Primary School) | 79.76 | Accuracy (%) | 92.6 |
| Open Arabic LLM - Alghafa Multiple Choice Facts Truefalse Balanced Task | 94.67 | Accuracy (%) | 92.3 |
| Open Arabic LLM - Arabic MMLU General Knowledge | 69.56 | Accuracy (%) | 91 |
| Open Arabic LLM - Arabic MMLU History (Middle School) | 72.41 | Accuracy (%) | 90.7 |
| Open Arabic LLM - Arabic MMLU Islamic Studies | 66.2 | Accuracy (%) | 89.8 |
Interactive version: theaggregate.ai/model?slug=yehia-7b-preview · How It Works · Data refreshed daily, snapshot 2026-11-05.