airoboros-7B-gpt4-1.4: benchmark results
Provider: Jon Durbin. Access: Open.
Aggregate Rating 1240 ± 15, rank #9345 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - HellaSwag | 61.14 | Accuracy (%) | 64.9 |
| MMLU-by-task - Global Facts | 34 | Accuracy (%) | 58.4 |
| MMLU-by-task - College Chemistry | 35 | Accuracy (%) | 56.4 |
| MMLU-by-task - Professional Medicine | 47.79 | Accuracy (%) | 53.6 |
| MMLU-by-task - ARC Challenge | 50.43 | Accuracy (%) | 53 |
| MMLU-by-task - Abstract Algebra | 30 | Accuracy (%) | 52.2 |
| MMLU-by-task - International Law | 62.81 | Accuracy (%) | 51.8 |
| MMLU-by-task - High School Mathematics | 26.67 | Accuracy (%) | 45.9 |
| MMLU-by-task - TruthfulQA MC1 | 27.42 | Accuracy (%) | 45.8 |
| MMLU-by-task - Public Relations | 50.91 | Accuracy (%) | 45.1 |
| MMLU-by-task - Astronomy | 40.13 | Accuracy (%) | 44 |
| MMLU-by-task - Professional Psychology | 40.36 | Accuracy (%) | 43.7 |
Interactive version: theaggregate.ai/model?slug=airoboros-7b-gpt4-1-4 · How It Works · Data refreshed daily, snapshot 2026-11-08.