mamba-gpt-3B-v4: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1170 ± 16, rank #9766 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Physics | 33.33 | Accuracy (%) | 83.7 |
| MMLU-by-task - Abstract Algebra | 31 | Accuracy (%) | 60.2 |
| MMLU-by-task - Elementary Mathematics | 29.89 | Accuracy (%) | 56.4 |
| MMLU-by-task - High School Mathematics | 27.41 | Accuracy (%) | 54.7 |
| MMLU-by-task - Global Facts | 32 | Accuracy (%) | 44.3 |
| MMLU-by-task - Moral Scenarios | 24.8 | Accuracy (%) | 41.6 |
| MMLU-by-task - College Computer Science | 34 | Accuracy (%) | 39.6 |
| MMLU-by-task - High School Statistics | 33.33 | Accuracy (%) | 38.3 |
| MMLU-by-task - College Mathematics | 30 | Accuracy (%) | 38.1 |
| MMLU-by-task - HellaSwag | 53.49 | Accuracy (%) | 36.6 |
| MMLU-by-task - High School European History | 33.94 | Accuracy (%) | 36.1 |
| MMLU-by-task - Public Relations | 39.09 | Accuracy (%) | 35.8 |
Interactive version: theaggregate.ai/model?slug=mamba-gpt-3b-v4 · How It Works · Data refreshed daily, snapshot 2026-11-08.