ArcaneEntanglement-model64-70B: benchmark results
ChuckMcSneed's linear merge of WinterGoddess, WizardLM, Spicyboros, Euryale, Xwin and Dolphin releases, with per-layer weight schedules in its published mergekit recipe. It remains distinct from each parent and from separately evaluated quantized conversions. Provider: ChuckMcSneed. Access: Open.
Aggregate Rating 1476 ± 33, rank #2726 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 70.83 | Accuracy (%) (5-shot) | 94.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 71.42 | Normalized accuracy (%) (25-shot) | 89.2 |
| Open LLM Leaderboard v1 - HellaSwag | 87.96 | Normalized accuracy (%) (10-shot) | 88.9 |
| Open LLM Leaderboard v1 - WinoGrande | 83.03 | Accuracy (%) (5-shot) | 86.8 |
| Open LLM Leaderboard v1 - GSM8K | 63 | Accuracy (%) (5-shot) | 76.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 60.53 | MC2 (%) (0-shot) | 76.1 |
Interactive version: theaggregate.ai/model?slug=arcaneentanglement-model64-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.