Llama3-Chinese-8B-Instruct: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1393 ± 26, rank #6426 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 55.8 | Accuracy (%) (5-shot) | 67.5 |
| Open LLM Leaderboard v1 - MMLU | 62.47 | Accuracy (%) (5-shot) | 55.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.5 | MC2 (%) (0-shot) | 52.1 |
| Open Chinese LLM - C-Eval Semantic | 67.74 | Accuracy (%) | 44.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 59.04 | Normalized accuracy (%) (25-shot) | 41.9 |
| Open Chinese LLM - CMMLU | 50.8 | Accuracy (%) | 37.3 |
| Open Chinese LLM - WinoGrande | 61.96 | Accuracy (%) | 34.3 |
| Open LLM Leaderboard v1 - WinoGrande | 73.95 | Accuracy (%) (5-shot) | 34.2 |
| Open Chinese LLM - TruthfulQA MC | 52.11 | Accuracy (%) | 33.7 |
| Open LLM Leaderboard v1 - HellaSwag | 78.23 | Normalized accuracy (%) (10-shot) | 33.3 |
| Open Chinese LLM - GSM8K | 36.09 | Accuracy (%) | 32 |
| Open Chinese LLM Leaderboard | 52.56 | Official Nonzero-Task Mean (%) | 25.1 |
Interactive version: theaggregate.ai/model?slug=llama3-chinese-8b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.