Bagel-Hermes-34B-Slerp: benchmark results
Weyaxi's SLERP merge of Jon Durbin's Bagel DPO 34B variants with Nous-Hermes 2 Yi 34B. Provider: Weyaxi. Released 2024-01-12. Access: Open.
Aggregate Rating 1521 ± 23, rank #715 of 1656 rated models, from 25 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 77.29 | Accuracy (%) (5-shot) | 98.5 |
| Open Portuguese LLM - FaQuAD NLI | 83.79 | Macro F1 (%) | 97.3 |
| Open Chinese LLM - WinoGrande | 71.59 | Accuracy (%) | 96.9 |
| Open Chinese LLM Leaderboard | 70.82 | Official Nonzero-Task Mean (%) | 96.7 |
| Open Chinese LLM - C-Eval Semantic | 90.39 | Accuracy (%) | 94.4 |
| Open Chinese LLM - HellaSwag | 69.92 | Accuracy (%) | 93.5 |
| Open Chinese LLM - ARC Challenge | 63.14 | Accuracy (%) | 93.2 |
| Open LLM Leaderboard v1 - WinoGrande | 84.37 | Accuracy (%) (5-shot) | 93.1 |
| Open Portuguese LLM - BLUEX | 67.59 | Accuracy (%) | 90.1 |
| Open LLM Leaderboard - MuSR | 46.22 | Score | 88.6 |
| Open Portuguese LLM - OAB Exams | 55.13 | Accuracy (%) | 87.7 |
| Open Chinese LLM - CMMLU | 70.5 | Accuracy (%) | 87 |
Interactive version: theaggregate.ai/model?slug=bagel-hermes-34b-slerp · How It Works · Data refreshed daily, snapshot 2026-10-20.