AceGPT-v2-70B-Chat: benchmark results
FreedomIntelligence/KAUST's AceGPT v2 70B Chat, a dialogue-tuned Arabic-focused LLM fine-tuned from AceGPT-v2-70B, part of the AceGPT family spanning 7B to 70B. Provider: FreedomIntelligence. Released 2024-06-17. Access: Open.
Aggregate Rating 1609 ± 24, rank #408 of 1661 rated models, from 256 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Arabic LLM - Arabic MMLU HT High School Government AND Politics | 89.64 | Accuracy (%) | 97.5 |
| Open Arabic LLM - Arabic MMLU HT Marketing | 86.32 | Accuracy (%) | 97.2 |
| Open Arabic LLM - Arabic MMLU HT International LAW | 81.82 | Accuracy (%) | 96.3 |
| Open Arabic LLM - Arabic MMLU HT Anatomy | 59.26 | Accuracy (%) | 93.8 |
| Open Arabic LLM - Alghafa Multiple Choice Rating Sentiment Task | 56.21 | Accuracy (%) | 93.2 |
| Open Arabic LLM - Arabic MMLU HT High School Geography | 84.34 | Accuracy (%) | 93.2 |
| Open Arabic LLM - Arabic MMLU HT Human Sexuality | 76.34 | Accuracy (%) | 92.9 |
| Open Arabic LLM - Alghafa Meta AR Dialects | 82.74 | Accuracy (%) | 92.6 |
| Open Arabic LLM - Arabic MMLU HT Human Aging | 71.3 | Accuracy (%) | 92.6 |
| Open Arabic LLM - Arabic MMLU HT High School Psychology | 84.22 | Accuracy (%) | 92 |
| Open Arabic LLM - Arabic MMLU HT Medical Genetics | 74 | Accuracy (%) | 92 |
| Open Arabic LLM - Arabic MMLU HT Nutrition | 77.45 | Accuracy (%) | 92 |
Interactive version: theaggregate.ai/model?slug=acegpt-v2-70b-chat · How It Works · Data refreshed daily, snapshot 2026-10-23.