ALARB — leaderboard
Arabic Legal Argument Reasoning Benchmark for evaluating LLM reasoning over Saudi commercial court cases and legal arguments.
Metric: Facts+regulations correct (self-reported). Source: benchmarklist.com. Status: saturation imminent. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 46 |
| 2 | Qwen 3 14B | 44.6 |
| 3 | aya-expanse-32B | 36.3 |
| 4 | Qwen 3 8B | 32.2 |
| 5 | Gemma 3 12B | 29.6 |
| 6 | O4 Mini | 27.6 |
| 7 | aya-expanse-8B | 24.6 |
| 8 | Gemma 3 4B | 24.5 |
Interactive version: theaggregate.ai/benchmark?slug=alarb · How the rankings work · Data refreshed daily, snapshot 2026-07-22.