ZephRP-m7B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1366 ± 44, rank #7284 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Chinese LLM - TruthfulQA MC | 56.12 | Accuracy (%) | 66 |
| Open Portuguese LLM - FaQuAD NLI | 69.92 | Macro F1 (%) | 60 |
| Open Portuguese LLM - OAB Exams | 41.78 | Accuracy (%) | 49.2 |
| Open Portuguese LLM - ASSIN2 RTE | 89.15 | Macro F1 (%) | 48.4 |
| Open Portuguese LLM - ENEM | 58.43 | Accuracy (%) | 43.9 |
| Open Portuguese LLM - BLUEX | 47.84 | Accuracy (%) | 40.2 |
| Open Chinese LLM - ARC Challenge | 45.73 | Accuracy (%) | 17.6 |
| Open Chinese LLM - GSM8K | 21.61 | Accuracy (%) | 13.9 |
| Open Chinese LLM - C-Eval Semantic | 51.53 | Accuracy (%) | 12.1 |
| Open Chinese LLM - CMMLU | 44.53 | Accuracy (%) | 11.5 |
| Open Chinese LLM - HellaSwag | 52.23 | Accuracy (%) | 10.7 |
| Open Chinese LLM - WinoGrande | 59.12 | Accuracy (%) | 10.7 |
Interactive version: theaggregate.ai/model?slug=zephrp-m7b · How It Works · Data refreshed daily, snapshot 2026-11-08.