Moko-SAMPLE: benchmark results
Azazelle's sample_ties merge, whose published recipe uses mistralai/Mistral-7B-v0.1 as its base and Open-Orca/Mistral-7B-OpenOrca, akjindal53244/Mistral-7B-v0.1-Open-Platypus, WizardLM/WizardMath-7B-V1.1 as merge inputs. Its published Mistral configuration specifies 32 decoder layers. Provider: Azazelle. Access: Open.
Aggregate Rating 1409 ± 33, rank #5659 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 64.57 | Accuracy (%) (5-shot) | 72.7 |
| Open LLM Leaderboard v1 - WinoGrande | 79.16 | Accuracy (%) (5-shot) | 67.7 |
| Open LLM Leaderboard v1 - HellaSwag | 83.85 | Normalized accuracy (%) (10-shot) | 62 |
| Open LLM Leaderboard v1 - GSM8K | 41.93 | Accuracy (%) (5-shot) | 56.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.09 | Normalized accuracy (%) (25-shot) | 51.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 43.45 | MC2 (%) (0-shot) | 23.5 |
Interactive version: theaggregate.ai/model?slug=moko-sample · How It Works · Data refreshed daily, snapshot 2026-11-08.