KingNish-Llama3-8B: benchmark results
Provider: Other.
Aggregate Rating 1455 ± 34, rank #3537 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 68.45 | Accuracy (%) (5-shot) | 91.5 |
| Open LLM Leaderboard v1 - GSM8K | 69.07 | Accuracy (%) (5-shot) | 87.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 69.97 | Normalized accuracy (%) (25-shot) | 84.7 |
| Open LLM Leaderboard v1 - HellaSwag | 85.83 | Normalized accuracy (%) (10-shot) | 77 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 61.02 | MC2 (%) (0-shot) | 76.9 |
| Open LLM Leaderboard v1 - WinoGrande | 78.37 | Accuracy (%) (5-shot) | 62.7 |
Interactive version: theaggregate.ai/model?slug=kingnish-llama3-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.