chinese-mixtral-instruct: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1464 ± 26, rank #3083 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 71.53 | Accuracy (%) (5-shot) | 95.1 |
| Open LLM Leaderboard v1 - WinoGrande | 83.11 | Accuracy (%) (5-shot) | 87.1 |
| Open Chinese LLM - WinoGrande | 66.38 | Accuracy (%) | 78 |
| Open LLM Leaderboard v1 - ARC Challenge | 67.75 | Normalized accuracy (%) (25-shot) | 78 |
| Open LLM Leaderboard v1 - HellaSwag | 85.67 | Normalized accuracy (%) (10-shot) | 75.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 57.46 | MC2 (%) (0-shot) | 70.1 |
| Open LLM Leaderboard v1 - GSM8K | 55.65 | Accuracy (%) (5-shot) | 67.3 |
| Open Chinese LLM - HellaSwag | 62.12 | Accuracy (%) | 66.1 |
| Open Chinese LLM - CMMLU | 56.39 | Accuracy (%) | 60.9 |
| Open Chinese LLM - TruthfulQA MC | 54.95 | Accuracy (%) | 59.8 |
| Open Chinese LLM - ARC Challenge | 53.5 | Accuracy (%) | 56.8 |
| Open Chinese LLM Leaderboard | 57.56 | Official Nonzero-Task Mean (%) | 54.4 |
Interactive version: theaggregate.ai/model?slug=chinese-mixtral-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.