ARIA-70B-V3: benchmark results
Provider: Rhymes AI. Access: Open.
Aggregate Rating 1404 ± 15, rank #5904 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Computer Science | 59 | Accuracy (%) | 98.1 |
| MMLU-by-task - High School Physics | 44.37 | Accuracy (%) | 95.5 |
| MMLU-by-task - Marketing | 89.32 | Accuracy (%) | 94.9 |
| MMLU-by-task - High School European History | 82.42 | Accuracy (%) | 94.7 |
| MMLU-by-task - Sociology | 86.57 | Accuracy (%) | 94.1 |
| MMLU-by-task - High School Chemistry | 50.25 | Accuracy (%) | 93.8 |
| MMLU-by-task - High School US History | 87.75 | Accuracy (%) | 93.6 |
| MMLU-by-task - Machine Learning | 49.11 | Accuracy (%) | 93.5 |
| MMLU-by-task - Professional Accounting | 51.77 | Accuracy (%) | 93.5 |
| MMLU-by-task - High School Government And Politics | 90.67 | Accuracy (%) | 93.4 |
| MMLU-by-task - World Religions | 83.63 | Accuracy (%) | 93.4 |
| MMLU-by-task - College Medicine | 61.27 | Accuracy (%) | 93.3 |
Interactive version: theaggregate.ai/model?slug=aria-70b-v3 · How It Works · Data refreshed daily, snapshot 2026-11-08.