dolphin-2.6-mistral-7B-dpo-5.93B: benchmark results
Mihaiii pruned derivative of Dolphin 2.6 Mistral 7B DPO with six decoder layers removed. Provider: Mihaiii. Access: Open.
Aggregate Rating 1170 ± 39, rank #9764 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 53.51 | MC2 (%) (0-shot) | 59.8 |
| Open LLM Leaderboard v1 - WinoGrande | 62.67 | Accuracy (%) (5-shot) | 15.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 38.99 | Normalized accuracy (%) (25-shot) | 15.5 |
| Open LLM Leaderboard v1 - MMLU | 27.32 | Accuracy (%) (5-shot) | 15 |
| Open LLM Leaderboard v1 - HellaSwag | 61.01 | Normalized accuracy (%) (10-shot) | 14.9 |
| Open LLM Leaderboard v1 - GSM8K | 0.23 | Accuracy (%) (5-shot) | 10.7 |
Interactive version: theaggregate.ai/model?slug=dolphin-2-6-mistral-7b-dpo-5-93b · How It Works · Data refreshed daily, snapshot 2026-11-08.