llama-3-chinese-8B-instruct: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1408 ± 26, rank #5724 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 55.15 | MC2 (%) (0-shot) | 64.3 |
| Open Chinese LLM - WinoGrande | 63.69 | Accuracy (%) | 59.8 |
| Open LLM Leaderboard v1 - GSM8K | 44.43 | Accuracy (%) (5-shot) | 58.5 |
| Open LLM Leaderboard v1 - MMLU | 63.1 | Accuracy (%) (5-shot) | 58.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.26 | Normalized accuracy (%) (25-shot) | 52 |
| Open Chinese LLM - C-Eval Semantic | 69.49 | Accuracy (%) | 50.3 |
| Open Chinese LLM - HellaSwag | 59.08 | Accuracy (%) | 42.8 |
| Open Chinese LLM Leaderboard | 56.34 | Official Nonzero-Task Mean (%) | 41.1 |
| Open LLM Leaderboard v1 - HellaSwag | 80.24 | Normalized accuracy (%) (10-shot) | 40.4 |
| Open LLM Leaderboard v1 - WinoGrande | 75.06 | Accuracy (%) (5-shot) | 40.1 |
| Open Chinese LLM - CMMLU | 51.39 | Accuracy (%) | 38.5 |
| Open Chinese LLM - TruthfulQA MC | 52.52 | Accuracy (%) | 37.6 |
Interactive version: theaggregate.ai/model?slug=llama-3-chinese-8b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.