Mocha-Sample-7B-ex: 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. The card heading retains another label; the exact repository and its recipe define this publication, without a global name alias. Provider: Azazelle. Access: Open.
Aggregate Rating 1411 ± 33, rank #5578 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 56.56 | Accuracy (%) (5-shot) | 68.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 64.76 | Normalized accuracy (%) (25-shot) | 67.9 |
| Open LLM Leaderboard v1 - HellaSwag | 84.35 | Normalized accuracy (%) (10-shot) | 65.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 54.18 | MC2 (%) (0-shot) | 61.8 |
| Open LLM Leaderboard v1 - MMLU | 62.2 | Accuracy (%) (5-shot) | 54.4 |
| Open LLM Leaderboard v1 - WinoGrande | 77.11 | Accuracy (%) (5-shot) | 53.3 |
Interactive version: theaggregate.ai/model?slug=mocha-sample-7b-ex · How It Works · Data refreshed daily, snapshot 2026-11-08.