v1olet_merged_dpo_7B_v4: benchmark results
Provider: Other.
Aggregate Rating 1406 ± 37, rank #5796 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 81.06 | Accuracy (%) (5-shot) | 77 |
| Open LLM Leaderboard v1 - ARC Challenge | 66.98 | Normalized accuracy (%) (25-shot) | 75.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 59.43 | MC2 (%) (0-shot) | 73.7 |
| Open LLM Leaderboard v1 - HellaSwag | 84.09 | Normalized accuracy (%) (10-shot) | 63.7 |
| Open LLM Leaderboard v1 - GSM8K | 35.25 | Accuracy (%) (5-shot) | 51 |
| Open LLM Leaderboard v1 - MMLU | 59.02 | Accuracy (%) (5-shot) | 44.5 |
Interactive version: theaggregate.ai/model?slug=v1olet-merged-dpo-7b-v4 · How It Works · Data refreshed daily, snapshot 2026-11-08.