Hala 1.2B: benchmark results

Provider: Other.

Aggregate Rating 1305 ± 41, rank #8574 of 10552 rated models, from 28 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Jais 3 Model Cards - AraGen v3 - Conciseness14.43C3H Conciseness (%)41.1
Jais 3 Model Cards - SimpleQA Verified (Arabic) - F-score3.1F-score (%)25
Jais 3 Model Cards - SimpleQA Verified (Arabic) - Non-hallucination Rate3.2Non-hallucination rate (%)16.1
Jais 3 Model Cards - AraGen v3 (3C3H)253C3H Score (%)14.3
Jais 3 Model Cards - IslamicEval 2025-1B (IFM-audited)35.5Accuracy (%)10.7
Jais 3 Model Cards - Alyah (IFM-audited)53.2Accuracy (%)5.4
Jais 3 Model Cards - AraSTEM (IFM-audited)48.3Accuracy (%)3.6
Jais 3 Model Cards - ArabCulture (IFM-audited)60.6Accuracy (%)3.6
Jais 3 Model Cards - Arabic Cuisine (IFM)49.5Accuracy (%)3.6
Jais 3 Model Cards - Arabic GSM8K (IFM-audited)57.3Accuracy (%)3.6
Jais 3 Model Cards - Arabic IFEval44.1Accuracy (%)3.6
Jais 3 Model Cards - Arabic Linguistics - Diacritization (IFM)32.9Accuracy (%)3.6

Interactive version: theaggregate.ai/model?slug=hala-1-2b · How It Works · Data refreshed daily, snapshot 2026-11-16.