ARIA-70B-V2: benchmark results
Provider: Rhymes AI. Access: Open.
Aggregate Rating 1395 ± 15, rank #6305 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Mathematics | 35.19 | Accuracy (%) | 98 |
| MMLU-by-task - College Computer Science | 57 | Accuracy (%) | 96.4 |
| MMLU-by-task - Global Facts | 46 | Accuracy (%) | 94.9 |
| MMLU-by-task - Sociology | 87.06 | Accuracy (%) | 94.9 |
| MMLU-by-task - Machine Learning | 50 | Accuracy (%) | 94.5 |
| MMLU-by-task - High School Chemistry | 50.25 | Accuracy (%) | 93.8 |
| MMLU-by-task - High School Physics | 42.38 | Accuracy (%) | 93.7 |
| MMLU-by-task - High School World History | 85.65 | Accuracy (%) | 93.6 |
| MMLU-by-task - Jurisprudence | 80.56 | Accuracy (%) | 93.6 |
| MMLU-by-task - World Religions | 83.63 | Accuracy (%) | 93.4 |
| MMLU-by-task - Human Aging | 73.99 | Accuracy (%) | 93.3 |
| MMLU-by-task - International Law | 82.64 | Accuracy (%) | 93.3 |
Interactive version: theaggregate.ai/model?slug=aria-70b-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.