Tulpar-tv_marcoroni-7B: benchmark results
Provider: Other.
Aggregate Rating 1202 ± 20, rank #9609 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC2 | 49.38 | Accuracy (%) | 73.3 |
| MMLU-by-task - TruthfulQA MC1 | 30.35 | Accuracy (%) | 59.4 |
| MMLU-by-task - Global Facts | 33 | Accuracy (%) | 51.6 |
| MMLU-by-task - Business Ethics | 46 | Accuracy (%) | 47.1 |
| MMLU-by-task - Machine Learning | 31.25 | Accuracy (%) | 43.7 |
| MMLU-by-task - High School World History | 53.16 | Accuracy (%) | 43.1 |
| MMLU-by-task - Virology | 37.35 | Accuracy (%) | 41.2 |
| MMLU-by-task - High School US History | 44.61 | Accuracy (%) | 40.7 |
| MMLU-by-task - High School Computer Science | 38 | Accuracy (%) | 40.5 |
| MMLU-by-task - High School European History | 44.24 | Accuracy (%) | 40 |
| MMLU-by-task - Prehistory | 41.05 | Accuracy (%) | 39.5 |
| MMLU-by-task - Anatomy | 39.26 | Accuracy (%) | 39.1 |
Interactive version: theaggregate.ai/model?slug=tulpar-tv-marcoroni-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.