Llama-3-8B-Instruct-abliterated [bfloat16] [rev: dd67dd055661]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1344 ± 34, rank #7853 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 41.47 | Accuracy (%) (5-shot) | 56.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 47.91 | MC2 (%) (0-shot) | 39.1 |
| Open LLM Leaderboard v1 - MMLU | 56.21 | Accuracy (%) (5-shot) | 38.5 |
| Open LLM Leaderboard v1 - WinoGrande | 71.35 | Accuracy (%) (5-shot) | 26.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 51.45 | Normalized accuracy (%) (25-shot) | 25.9 |
| Open LLM Leaderboard v1 - HellaSwag | 74.02 | Normalized accuracy (%) (10-shot) | 24.2 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-instruct-abliterated-bfloat16-rev-dd67dd055661 · How It Works · Data refreshed daily, snapshot 2026-11-08.