GPT-J-6B-Skein: benchmark results
Provider: KoboldAI. Access: Open.
Aggregate Rating 1141 ± 16, rank #10098 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Machine Learning | 29.46 | Accuracy (%) | 35.2 |
| MMLU-by-task - High School Mathematics | 25.93 | Accuracy (%) | 34.1 |
| MMLU-by-task - Jurisprudence | 31.48 | Accuracy (%) | 32.8 |
| MMLU-by-task - HellaSwag | 50.78 | Accuracy (%) | 32.3 |
| MMLU-by-task - ARC Challenge | 38.57 | Accuracy (%) | 31.7 |
| MMLU-by-task - Public Relations | 34.55 | Accuracy (%) | 31.7 |
| MMLU-by-task - Human Aging | 36.32 | Accuracy (%) | 31.2 |
| MMLU-by-task - Miscellaneous | 30.4 | Accuracy (%) | 30.5 |
| MMLU-by-task - Virology | 31.93 | Accuracy (%) | 30 |
| MMLU-by-task - Conceptual Physics | 31.91 | Accuracy (%) | 29.5 |
| MMLU-by-task - Abstract Algebra | 26 | Accuracy (%) | 28.1 |
| MMLU-by-task - High School Chemistry | 27.59 | Accuracy (%) | 27.4 |
Interactive version: theaggregate.ai/model?slug=gpt-j-6b-skein · How It Works · Data refreshed daily, snapshot 2026-11-08.