NeuralLLaMa-3-8B-ORPO-v0.4: benchmark results
Provider: Other. Released 2024-05-16. Access: Open.
Aggregate Rating 1410 ± 17, rank #1189 of 1656 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 49.81 | Exact match, flexible extract (%) | 83.8 |
| Open Korean LLM - Ko-IFEval | 39.7 | Strict accuracy, prompt/instruction mean (%) | 81.3 |
| Open Korean LLM Leaderboard | 39.63 | Average Score (%) | 72.8 |
| Open Ko-LLM Leaderboard | 39.63 | Average (%) | 72.6 |
| Open Chinese LLM - GSM8K | 48.9 | Accuracy (%) | 63.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| Open Portuguese LLM - OAB Exams | 45.69 | Accuracy (%) | 61.9 |
| Open Chinese LLM - TruthfulQA MC | 54.83 | Accuracy (%) | 58.3 |
| Open Korean LLM - Ko-EQ-Bench | 12.51 | EQ-Bench score | 58.3 |
| Open Portuguese LLM - ENEM | 63.54 | Accuracy (%) | 56 |
| Open Chinese LLM - WinoGrande | 63.38 | Accuracy (%) | 55.6 |
| Open Chinese LLM - CMMLU | 54.23 | Accuracy (%) | 55 |
Interactive version: theaggregate.ai/model?slug=neuralllama-3-8b-orpo-v0-4 · How It Works · Data refreshed daily, snapshot 2026-10-20.