airoboros-l2-13B-gpt4-2.0: benchmark results
Provider: Jon Durbin. Access: Open.
Aggregate Rating 1338 ± 15, rank #8005 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Human Aging | 69.06 | Accuracy (%) | 90.3 |
| MMLU-by-task - Business Ethics | 62 | Accuracy (%) | 89.9 |
| MMLU-by-task - High School Physics | 37.09 | Accuracy (%) | 88.1 |
| MMLU-by-task - Computer Security | 71 | Accuracy (%) | 86.2 |
| MMLU-by-task - US Foreign Policy | 83 | Accuracy (%) | 83.1 |
| MMLU-by-task - Econometrics | 34.21 | Accuracy (%) | 82.6 |
| MMLU-by-task - Abstract Algebra | 34 | Accuracy (%) | 82 |
| MMLU-by-task - Global Facts | 38 | Accuracy (%) | 81.7 |
| MMLU-by-task - HellaSwag | 62.96 | Accuracy (%) | 80.7 |
| MMLU-by-task - Professional Law | 42.96 | Accuracy (%) | 80.4 |
| MMLU-by-task - High School Biology | 66.13 | Accuracy (%) | 78.2 |
| MMLU-by-task - High School Geography | 70.71 | Accuracy (%) | 77.3 |
Interactive version: theaggregate.ai/model?slug=airoboros-l2-13b-gpt4-2-0 · How It Works · Data refreshed daily, snapshot 2026-11-08.