Argetsu: benchmark results
Azazelle's SLERP merge, whose published recipe uses mistralai/Mistral-7B-v0.1 as its base and Azazelle/SlimMelodicMaid, Azazelle/Dumb-Maidlet as merge inputs. Its published Mistral configuration specifies 32 decoder layers. Provider: Azazelle. Access: Open.
Aggregate Rating 1436 ± 33, rank #4366 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 65.55 | Accuracy (%) (5-shot) | 84.8 |
| Open LLM Leaderboard v1 - HellaSwag | 86.32 | Normalized accuracy (%) (10-shot) | 80.2 |
| Open LLM Leaderboard v1 - GSM8K | 63.31 | Accuracy (%) (5-shot) | 76.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 67.06 | Normalized accuracy (%) (25-shot) | 75.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 56.46 | MC2 (%) (0-shot) | 68.1 |
| Open LLM Leaderboard v1 - WinoGrande | 79.16 | Accuracy (%) (5-shot) | 67.7 |
Interactive version: theaggregate.ai/model?slug=argetsu · How It Works · Data refreshed daily, snapshot 2026-11-08.