Llama 3 8B Ultrafeedback Dpo: benchmark results
An ibivibiv checkpoint with a published Llama configuration and 32 decoder layers. The model card leaves training details unspecified. Provider: ibivibiv. Access: Open.
Aggregate Rating 1265 ± 38, rank #9121 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 55.04 | MC2 (%) (0-shot) | 64.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 50.68 | Normalized accuracy (%) (25-shot) | 25 |
| Open LLM Leaderboard v1 - HellaSwag | 72.84 | Normalized accuracy (%) (10-shot) | 23.3 |
| Open LLM Leaderboard v1 - MMLU | 41.53 | Accuracy (%) (5-shot) | 21.7 |
| Open LLM Leaderboard v1 - WinoGrande | 64.64 | Accuracy (%) (5-shot) | 17.6 |
| Open LLM Leaderboard v1 - GSM8K | 0.61 | Accuracy (%) (5-shot) | 13.1 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-ultrafeedback-dpo · How It Works · Data refreshed daily, snapshot 2026-11-08.