RedTulu-Uncensored-3B-0719: benchmark results
heegyu's RedTulu release based on togethercomputer/RedPajama-INCITE-Base-3B-v1. The card identifies AllenAI's open-instruct data and reports processing it using code from ehartford/wizard_vicuna_70k_unfiltered; it remains distinct from the OpenLLaMA-based WizardVicuna releases. Provider: heegyu. Access: Open.
Aggregate Rating 1167 ± 16, rank #9788 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - High School Physics | 37.75 | Accuracy (%) | 89.6 |
| MMLU-by-task - Formal Logic | 35.71 | Accuracy (%) | 72.7 |
| MMLU-by-task - Moral Scenarios | 27.26 | Accuracy (%) | 59.8 |
| MMLU-by-task - College Mathematics | 32 | Accuracy (%) | 53.7 |
| MMLU-by-task - High School Statistics | 37.96 | Accuracy (%) | 48.7 |
| MMLU-by-task - College Physics | 24.51 | Accuracy (%) | 48.1 |
| MMLU-by-task - Econometrics | 28.07 | Accuracy (%) | 47.3 |
| MMLU-by-task - College Chemistry | 32 | Accuracy (%) | 46.9 |
| MMLU-by-task - Global Facts | 32 | Accuracy (%) | 44.3 |
| MMLU-by-task - Elementary Mathematics | 27.51 | Accuracy (%) | 43.5 |
| MMLU-by-task - High School Macroeconomics | 37.18 | Accuracy (%) | 41.6 |
| MMLU-by-task - High School Mathematics | 26.3 | Accuracy (%) | 40 |
Interactive version: theaggregate.ai/model?slug=redtulu-uncensored-3b-0719 · How It Works · Data refreshed daily, snapshot 2026-11-08.