Marcoroni-70B-v1: benchmark results
Provider: Other.
Aggregate Rating 1443 ± 18, rank #4089 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Medicine | 70.52 | Accuracy (%) | 100 |
| MMLU-by-task - Moral Scenarios | 66.82 | Accuracy (%) | 100 |
| MMLU-by-task - ARC Challenge | 68.77 | Accuracy (%) | 99.8 |
| MMLU-by-task - Conceptual Physics | 71.06 | Accuracy (%) | 99.8 |
| MMLU-by-task - TruthfulQA MC1 | 46.88 | Accuracy (%) | 99.8 |
| MMLU-by-task - Professional Psychology | 76.63 | Accuracy (%) | 99.6 |
| MMLU-by-task Leaderboard | 70.67 | MMLU Average (%) | 99.6 |
| MMLU-by-task - High School Macroeconomics | 73.08 | Accuracy (%) | 99.4 |
| MMLU-by-task - High School Microeconomics | 78.57 | Accuracy (%) | 99.4 |
| MMLU-by-task - Logical Fallacies | 83.44 | Accuracy (%) | 99.4 |
| MMLU-by-task - Machine Learning | 58.93 | Accuracy (%) | 99.4 |
| MMLU-by-task - TruthfulQA MC2 | 64.41 | Accuracy (%) | 99.4 |
Interactive version: theaggregate.ai/model?slug=marcoroni-70b-v1 · How It Works · Data refreshed daily, snapshot 2026-11-08.