llama-3-chinese-8B-instruct-v2: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1424 ± 26, rank #4961 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 66.48 | Accuracy (%) (5-shot) | 87.4 |
| Open LLM Leaderboard v1 - GSM8K | 60.58 | Accuracy (%) (5-shot) | 72.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 53.93 | MC2 (%) (0-shot) | 61.2 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.63 | Normalized accuracy (%) (25-shot) | 59 |
| Open Chinese LLM Leaderboard | 57.44 | Official Nonzero-Task Mean (%) | 53.6 |
| Open LLM Leaderboard v1 - WinoGrande | 76.72 | Accuracy (%) (5-shot) | 50.1 |
| Open Chinese LLM - C-Eval Semantic | 69.21 | Accuracy (%) | 49.4 |
| Open Chinese LLM - GSM8K | 44.81 | Accuracy (%) | 46 |
| Open Chinese LLM - CMMLU | 52.9 | Accuracy (%) | 45.3 |
| Open LLM Leaderboard v1 - HellaSwag | 79.72 | Normalized accuracy (%) (10-shot) | 38.9 |
| Open Chinese LLM - HellaSwag | 57.66 | Accuracy (%) | 34 |
| Open Chinese LLM - TruthfulQA MC | 52.02 | Accuracy (%) | 33.1 |
Interactive version: theaggregate.ai/model?slug=llama-3-chinese-8b-instruct-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.