MiquMaid-v2-2x70B-DPO: benchmark results
A mixture-of-experts release by NeverSleep, credited to Undi and IkariDev, combining MiquMaid-v2-70B-DPO and Miqu-70B-DPO. The card says both components underwent DPO and participate for each token; this is distinct from the single-model DPO release. Provider: NeverSleep. Access: Open.
Aggregate Rating 1506 ± 34, rank #2248 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 85.32 | Accuracy (%) (5-shot) | 98.1 |
| Open LLM Leaderboard v1 - MMLU | 75.31 | Accuracy (%) (5-shot) | 96.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 72.53 | Normalized accuracy (%) (25-shot) | 92.4 |
| Open LLM Leaderboard v1 - HellaSwag | 88.36 | Normalized accuracy (%) (10-shot) | 91.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 66.5 | MC2 (%) (0-shot) | 84.9 |
| Open LLM Leaderboard v1 - GSM8K | 67.32 | Accuracy (%) (5-shot) | 83.4 |
Interactive version: theaggregate.ai/model?slug=miqumaid-v2-2x70b-dpo · How It Works · Data refreshed daily, snapshot 2026-11-08.