NeuralLLaMa-3-8B-ORPO-v0.4: benchmark results
Provider: Other. Released 2024-05-16. Access: Open.
Unified ELO 1466 ± 1, rank #870 of 1392 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM Leaderboard | 39.62 | Average Score (%) | 69.4 |
| Open Chinese LLM - GSM8K | 48.9 | Accuracy (%) | 63.4 |
| Open Chinese LLM - TruthfulQA MC | 54.83 | Accuracy (%) | 58.5 |
| Open Chinese LLM - WinoGrande | 63.38 | Accuracy (%) | 55.8 |
| Open Chinese LLM - CMMLU | 54.23 | Accuracy (%) | 54.9 |
| Open Chinese LLM - C-Eval Semantic | 69.38 | Accuracy (%) | 49.9 |
| Open Chinese LLM Leaderboard | 56.46 | Average Score (%) | 47.6 |
| Open Chinese LLM - ARC Challenge | 48.21 | Accuracy (%) | 33.4 |
| Open Chinese LLM - HellaSwag | 56.29 | Accuracy (%) | 29.4 |
Interactive version: theaggregate.ai/model?slug=neuralllama-3-8b-orpo-v0-4 · How It Works · Data refreshed daily, snapshot 2026-09-05.