GPT-J-6B-Adventure: benchmark results
Provider: EleutherAI. Access: Open.
Aggregate Rating 1137 ± 16, rank #10173 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Econometrics | 32.46 | Accuracy (%) | 77.1 |
| MMLU-by-task - Moral Scenarios | 26.03 | Accuracy (%) | 51.7 |
| MMLU-by-task - Professional Accounting | 32.27 | Accuracy (%) | 42.9 |
| MMLU-by-task - High School Physics | 28.48 | Accuracy (%) | 39.1 |
| MMLU-by-task - Machine Learning | 30.36 | Accuracy (%) | 39 |
| MMLU-by-task - Formal Logic | 26.98 | Accuracy (%) | 35.6 |
| MMLU-by-task - Sociology | 34.83 | Accuracy (%) | 34.2 |
| MMLU-by-task - Jurisprudence | 31.48 | Accuracy (%) | 32.8 |
| MMLU-by-task - Human Sexuality | 29.77 | Accuracy (%) | 31.9 |
| MMLU-by-task - High School Microeconomics | 28.57 | Accuracy (%) | 29.2 |
| MMLU-by-task - Abstract Algebra | 26 | Accuracy (%) | 28.1 |
| MMLU-by-task - College Mathematics | 28 | Accuracy (%) | 27.8 |
Interactive version: theaggregate.ai/model?slug=gpt-j-6b-adventure · How It Works · Data refreshed daily, snapshot 2026-11-08.