Nous-Hermes-2-SUS-Chat-34B-Slerp: benchmark results
Weyaxi's Nous-Hermes-2-SUS-Chat-34B-Slerp, a mergekit SLERP merge of Nous-Hermes-2-Yi-34B and SUS-Chat-34B. Provider: Weyaxi. Released 2024-01-02. Access: Open.
Aggregate Rating 1503 ± 23, rank #769 of 1635 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 72.86 | Accuracy (%) (5-shot) | 98.2 |
| Open LLM Leaderboard v1 - MMLU | 77 | Accuracy (%) (5-shot) | 98.1 |
| Open Chinese LLM - WinoGrande | 70.24 | Accuracy (%) | 93.3 |
| Open Portuguese LLM - BLUEX | 68.01 | Accuracy (%) | 90.7 |
| Open LLM Leaderboard v1 - WinoGrande | 83.58 | Accuracy (%) (5-shot) | 89.7 |
| Open Portuguese LLM - OAB Exams | 56.08 | Accuracy (%) | 89.3 |
| Open Chinese LLM - HellaSwag | 68.64 | Accuracy (%) | 89.1 |
| Open Chinese LLM - C-Eval Semantic | 88.73 | Accuracy (%) | 88.5 |
| Open Portuguese LLM - FaQuAD NLI | 79.77 | Macro F1 (%) | 88.2 |
| Open Chinese LLM - ARC Challenge | 59.9 | Accuracy (%) | 86.8 |
| Open Chinese LLM - CMMLU | 70.42 | Accuracy (%) | 86.7 |
| Open Chinese LLM Leaderboard | 67.32 | Official Nonzero-Task Mean (%) | 86.4 |
Interactive version: theaggregate.ai/model?slug=nous-hermes-2-sus-chat-34b-slerp · How It Works · Data refreshed daily, snapshot 2026-11-05.