Snorkel-Mistral-PairRM-DPO [float16] [rev: e4110a5689e1]: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1407 ± 35, rank #5738 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 70.91 | MC2 (%) (0-shot) | 91 |
| Open LLM Leaderboard v1 - HellaSwag | 85.63 | Normalized accuracy (%) (10-shot) | 75.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 65.96 | Normalized accuracy (%) (25-shot) | 71.7 |
| Open LLM Leaderboard v1 - WinoGrande | 77.58 | Accuracy (%) (5-shot) | 57 |
| Open LLM Leaderboard v1 - GSM8K | 36.16 | Accuracy (%) (5-shot) | 51.6 |
| Open LLM Leaderboard v1 - MMLU | 60.85 | Accuracy (%) (5-shot) | 49.9 |
Interactive version: theaggregate.ai/model?slug=snorkel-mistral-pairrm-dpo-float16-rev-e4110a5689e1 · How It Works · Data refreshed daily, snapshot 2026-11-08.