Aura-Llama-Abliterated: benchmark results
Provider: Other.
Aggregate Rating 1331 ± 35, rank #8142 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 27.6 | Accuracy (%) (5-shot) | 45.4 |
| Open LLM Leaderboard v1 - MMLU | 55.71 | Accuracy (%) (5-shot) | 37.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.63 | MC2 (%) (0-shot) | 35 |
| Open LLM Leaderboard v1 - ARC Challenge | 49.23 | Normalized accuracy (%) (25-shot) | 23.8 |
| Open LLM Leaderboard v1 - WinoGrande | 69.3 | Accuracy (%) (5-shot) | 23.3 |
| Open LLM Leaderboard v1 - HellaSwag | 72.27 | Normalized accuracy (%) (10-shot) | 22.6 |
Interactive version: theaggregate.ai/model?slug=aura-llama-abliterated · How It Works · Data refreshed daily, snapshot 2026-11-08.