fairseq-dense-6.7B: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1142 ± 17, rank #10069 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Statistics | 43.98 | Accuracy (%) | 70 |
| MMLU-by-task - High School Mathematics | 27.78 | Accuracy (%) | 58.6 |
| MMLU-by-task - High School Physics | 31.13 | Accuracy (%) | 56.1 |
| MMLU-by-task - College Physics | 24.51 | Accuracy (%) | 48.1 |
| MMLU-by-task - Professional Medicine | 44.85 | Accuracy (%) | 45.7 |
| MMLU-by-task - Global Facts | 31 | Accuracy (%) | 36.8 |
| MMLU-by-task - High School Chemistry | 29.06 | Accuracy (%) | 36.1 |
| MMLU-by-task - HellaSwag | 52.88 | Accuracy (%) | 35.6 |
| MMLU-by-task - Security Studies | 36.33 | Accuracy (%) | 34 |
| MMLU-by-task - High School Computer Science | 33 | Accuracy (%) | 33.8 |
| MMLU-by-task - College Medicine | 30.06 | Accuracy (%) | 32.7 |
| MMLU-by-task - Moral Scenarios | 24.36 | Accuracy (%) | 32.6 |
Interactive version: theaggregate.ai/model?slug=fairseq-dense-6-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.