Llama-3-MahouDevil-8B: benchmark results
lemon07r's Llama-3-MahouDevil-8B is a Model Stock merge documented with a mergekit recipe. The recipe combines flammenai/Mahou-1.2-llama3-8B, flammenai/Mahou-1.3-llama3-8B, mlabonne/NeuralDaredevil-8B-abliterated. Provider: lemon07r. Access: Open.
Aggregate Rating 1455 ± 34, rank #3556 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 71.65 | Accuracy (%) (5-shot) | 96.3 |
| Open LLM Leaderboard v1 - MMLU | 68.64 | Accuracy (%) (5-shot) | 91.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 69.45 | Normalized accuracy (%) (25-shot) | 83.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 61.53 | MC2 (%) (0-shot) | 77.8 |
| Open LLM Leaderboard v1 - HellaSwag | 84.9 | Normalized accuracy (%) (10-shot) | 70 |
| Open LLM Leaderboard v1 - WinoGrande | 78.14 | Accuracy (%) (5-shot) | 60.9 |
Interactive version: theaggregate.ai/model?slug=llama-3-mahoudevil-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.