30B-Lazarus-instruct-PL-lora_unload: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1353 ± 15, rank #7625 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC2 | 55.49 | Accuracy (%) | 93.3 |
| MMLU-by-task - Anatomy | 55.56 | Accuracy (%) | 91.6 |
| MMLU-by-task - TruthfulQA MC1 | 37.82 | Accuracy (%) | 91.4 |
| MMLU-by-task - Medical Genetics | 67 | Accuracy (%) | 91.2 |
| MMLU-by-task - Elementary Mathematics | 39.42 | Accuracy (%) | 91.1 |
| MMLU-by-task - High School Geography | 77.78 | Accuracy (%) | 89.7 |
| MMLU-by-task - Global Facts | 40 | Accuracy (%) | 88.7 |
| MMLU-by-task - Astronomy | 63.82 | Accuracy (%) | 88.6 |
| MMLU-by-task - Professional Medicine | 58.82 | Accuracy (%) | 88.5 |
| MMLU-by-task - Conceptual Physics | 50.64 | Accuracy (%) | 87.7 |
| MMLU-by-task - High School European History | 73.33 | Accuracy (%) | 87.7 |
| MMLU-by-task - ARC Challenge | 59.73 | Accuracy (%) | 87.3 |
Interactive version: theaggregate.ai/model?slug=30b-lazarus-instruct-pl-lora-unload · How It Works · Data refreshed daily, snapshot 2026-11-08.