jais-adapted-7B-chat: benchmark results
Inception (G42) and Cerebras' Jais Adapted 7B Chat, fine-tuned from their Jais Adapted 7B base model, released under Apache 2.0. Provider: Inception (G42) & Cerebras. Released 2024-08-02. Access: Open.
Aggregate Rating 1416 ± 20, rank #1160 of 1640 rated models, from 275 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Arabic LLM - Arabic MMLU Economics (Middle School) | 79.31 | Accuracy (%) | 79.6 |
| HELM Arabic - Aratrust - Offensive | 92.75 | Exact Match (%) | 78.8 |
| HELM Arabic - Alghafa - Multiple Choice Rating Sentiment No Neutral Task | 82 | Exact Match (%) | 72.5 |
| HELM Arabic - Alghafa - Multiple Choice Rating Sentiment Task | 56.9 | Exact Match (%) | 70 |
| Open Arabic LLM - Alghafa Multiple Choice Rating Sentiment Task | 53.36 | Accuracy (%) | 69.8 |
| Open Arabic LLM - Alghafa Multiple Choice Sentiment Task | 39.88 | Accuracy (%) | 66.4 |
| Open Arabic LLM - Arabic MMLU Philosophy (High School) | 61.54 | Accuracy (%) | 61.1 |
| Open Arabic LLM - Arabic MMLU HT Global Facts | 36 | Accuracy (%) | 59.9 |
| Open Arabic LLM - Aratrust Offensive | 82.61 | Accuracy (%) | 57.5 |
| Open Arabic LLM - Arabic MMLU LAW (Professional) | 66.56 | Accuracy (%) | 55.9 |
| Open Arabic LLM - Alghafa Multiple Choice Grounded Statement Xglue Mlqa Task | 81.33 | Accuracy (%) | 54 |
| Open Arabic LLM - Alghafa Multiple Choice Grounded Statement Soqal Task | 81.33 | Accuracy (%) | 50.9 |
Interactive version: theaggregate.ai/model?slug=jais-adapted-7b-chat · How It Works · Data refreshed daily, snapshot 2026-10-13.