test-3B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1123 ± 16, rank #10479 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Statistics | 43.52 | Accuracy (%) | 68.1 |
| MMLU-by-task - TruthfulQA MC2 | 41.42 | Accuracy (%) | 33.4 |
| MMLU-by-task - Conceptual Physics | 32.77 | Accuracy (%) | 33.3 |
| MMLU-by-task - Logical Fallacies | 29.45 | Accuracy (%) | 29.3 |
| MMLU-by-task - High School Biology | 29.35 | Accuracy (%) | 28.7 |
| MMLU-by-task - Miscellaneous | 28.61 | Accuracy (%) | 25.7 |
| MMLU-by-task - Medical Genetics | 30 | Accuracy (%) | 25.6 |
| MMLU-by-task - Elementary Mathematics | 25.66 | Accuracy (%) | 24.3 |
| MMLU-by-task - Prehistory | 26.85 | Accuracy (%) | 22.1 |
| MMLU-by-task - High School Microeconomics | 24.37 | Accuracy (%) | 20.5 |
| MMLU-by-task - Professional Law | 24.9 | Accuracy (%) | 19.1 |
| MMLU-by-task - Electrical Engineering | 25.52 | Accuracy (%) | 18.3 |
Interactive version: theaggregate.ai/model?slug=test-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.