Configurable-Llama-3-8B-v0.2: benchmark results
Provider: vicgalle. Access: Open.
Aggregate Rating 1425 ± 35, rank #4926 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 70.2 | Accuracy (%) (5-shot) | 92 |
| Open LLM Leaderboard v1 - MMLU | 67.02 | Accuracy (%) (5-shot) | 88.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 56.79 | MC2 (%) (0-shot) | 68.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.54 | Normalized accuracy (%) (25-shot) | 58.6 |
| Open LLM Leaderboard v1 - WinoGrande | 75.14 | Accuracy (%) (5-shot) | 40.5 |
| Open LLM Leaderboard v1 - HellaSwag | 79.77 | Normalized accuracy (%) (10-shot) | 39.2 |
Interactive version: theaggregate.ai/model?slug=configurable-llama-3-8b-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.