xDAN-SlimOrca: benchmark results
Azazelle's SLERP merge, whose published recipe uses mistralai/Mistral-7B-v0.1 as its base and xDAN-AI/xDAN-L1-Chat-RL-v1, openaccess-ai-collective/mistral-7b-slimorcaboros as merge inputs. Its published Mistral configuration specifies 32 decoder layers. Provider: Azazelle. Access: Open.
Aggregate Rating 1422 ± 33, rank #5067 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 85.7 | Normalized accuracy (%) (10-shot) | 76.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 57.68 | MC2 (%) (0-shot) | 70.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 65.61 | Normalized accuracy (%) (25-shot) | 70.5 |
| Open LLM Leaderboard v1 - GSM8K | 57.92 | Accuracy (%) (5-shot) | 69.6 |
| Open LLM Leaderboard v1 - MMLU | 63.67 | Accuracy (%) (5-shot) | 62.3 |
| Open LLM Leaderboard v1 - WinoGrande | 77.66 | Accuracy (%) (5-shot) | 57.6 |
Interactive version: theaggregate.ai/model?slug=xdan-slimorca · How It Works · Data refreshed daily, snapshot 2026-11-08.