higgs-llama-vicuna-ep25-70B: benchmark results
Provider: Boson AI. Access: Open.
Aggregate Rating 1400 ± 15, rank #6091 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Jurisprudence | 83.33 | Accuracy (%) | 98.1 |
| MMLU-by-task - Public Relations | 73.64 | Accuracy (%) | 97.6 |
| MMLU-by-task - College Chemistry | 49 | Accuracy (%) | 95.8 |
| MMLU-by-task - High School Physics | 44.37 | Accuracy (%) | 95.5 |
| MMLU-by-task - Security Studies | 78.37 | Accuracy (%) | 95.5 |
| MMLU-by-task - College Computer Science | 55 | Accuracy (%) | 94.4 |
| MMLU-by-task - Business Ethics | 70 | Accuracy (%) | 94.1 |
| MMLU-by-task - College Medicine | 63.01 | Accuracy (%) | 94.1 |
| MMLU-by-task - Management | 81.55 | Accuracy (%) | 94.1 |
| MMLU-by-task - HellaSwag | 67.38 | Accuracy (%) | 93.5 |
| MMLU-by-task - Miscellaneous | 83.65 | Accuracy (%) | 93.5 |
| MMLU-by-task - Astronomy | 75 | Accuracy (%) | 93.4 |
Interactive version: theaggregate.ai/model?slug=higgs-llama-vicuna-ep25-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.