llama3-passthrough-chat: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1394 ± 30, rank #6353 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 51.38 | Normalized accuracy (%) | 90.3 |
| Open LLM Leaderboard v1 - MMLU | 67.47 | Accuracy (%) (5-shot) | 89.4 |
| Open Korean LLM - Ko-IFEval | 41.04 | Strict accuracy, prompt/instruction mean (%) | 83.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.76 | Normalized accuracy (%) | 81.3 |
| Open Korean LLM - KorNAT-Harmless | 63.85 | Normalized accuracy (%) | 67.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 52.55 | MC2 (%) (0-shot) | 56.5 |
| Open Korean LLM Leaderboard | 35.75 | Average Score (%) | 53.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 19.71 | Exact match, flexible extract (%) | 51.2 |
| Open LLM Leaderboard v1 - GSM8K | 34.34 | Accuracy (%) (5-shot) | 50.1 |
| Open Korean LLM - Ko-EQ-Bench | 1.09 | EQ-Bench score | 46.6 |
| Open Korean LLM - Ko-Winogrande | 59.04 | Accuracy (%) | 43.7 |
| Open Korean LLM - KorNAT-CKA | 21.92 | Normalized accuracy (%) | 37.4 |
Interactive version: theaggregate.ai/model?slug=llama3-passthrough-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.