dolphin-ultrafeedback-dpo: benchmark results
An ibivibiv checkpoint with a published Mistral configuration and 32 decoder layers. The model card leaves training details unspecified. Provider: ibivibiv. Access: Open.
Aggregate Rating 1415 ± 33, rank #5442 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 85.12 | Normalized accuracy (%) (10-shot) | 71.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 64.76 | Normalized accuracy (%) (25-shot) | 67.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 55.1 | MC2 (%) (0-shot) | 64.2 |
| Open LLM Leaderboard v1 - GSM8K | 46.32 | Accuracy (%) (5-shot) | 60.1 |
| Open LLM Leaderboard v1 - MMLU | 63.33 | Accuracy (%) (5-shot) | 59.9 |
| Open LLM Leaderboard v1 - WinoGrande | 77.9 | Accuracy (%) (5-shot) | 59.3 |
Interactive version: theaggregate.ai/model?slug=dolphin-ultrafeedback-dpo · How It Works · Data refreshed daily, snapshot 2026-11-08.