AceGPT-13B-chat: benchmark results
Provider: Other. Released 2023-09-21. Access: Open.
Unified ELO 1454 ± 30, rank #1496 of 2656 rated models, from 127 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Arabic LLM - Arabic MMLU HT College Mathematics | 36 | Accuracy (%) | 67 |
| Open Arabic LLM - Arabic MMLU Arabic Language (Primary School) | 62.7 | Accuracy (%) | 63.3 |
| Open Arabic LLM - Arabic MMLU LAW (Professional) | 68.47 | Accuracy (%) | 61.4 |
| Open Arabic LLM - Arabic MMLU Computer Science (University) | 60.94 | Accuracy (%) | 53.4 |
| Open Arabic LLM - Arabic MMLU HT Formal Logic | 38.89 | Accuracy (%) | 52.8 |
| Open Arabic LLM - Arabic MMLU Islamic Studies | 40.53 | Accuracy (%) | 52.2 |
| Open Arabic LLM - Arabic MMLU Social Science (Middle School) | 47.72 | Accuracy (%) | 50.6 |
| Open Arabic LLM - Arabic MMLU Islamic Studies (Primary School) | 67.07 | Accuracy (%) | 50 |
| Open Arabic LLM - Arabic MMLU General Knowledge (Primary School) | 61.11 | Accuracy (%) | 49.4 |
| Open Arabic LLM - Arabic MMLU History (Primary School) | 51.96 | Accuracy (%) | 49.4 |
| Open Arabic LLM - Arabic MMLU Natural Science (Middle School) | 61.57 | Accuracy (%) | 47.5 |
| Open Arabic LLM - Alghafa Multiple Choice Rating Sentiment Task | 51.13 | Accuracy (%) | 47.2 |
Interactive version: theaggregate.ai/model?slug=acegpt-13b-chat · How It Works · Data refreshed daily, snapshot 2026-09-19.