Unichat-llama3-Chinese-8B-28K: benchmark results
Provider: Other. Access: Open.
Unified ELO 1401 ± 16, rank #2136 of 2928 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 29.64 | Accuracy (%) (5-shot) | 46.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.74 | Normalized accuracy (%) (25-shot) | 36.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 47.01 | MC2 (%) (0-shot) | 36.1 |
| Open LLM Leaderboard v1 - MMLU | 55.27 | Accuracy (%) (5-shot) | 35.8 |
| Open LLM Leaderboard v1 - HellaSwag | 76.53 | Normalized accuracy (%) (10-shot) | 28.9 |
| Open LLM Leaderboard v1 - WinoGrande | 69.46 | Accuracy (%) (5-shot) | 23.5 |
| Open Chinese LLM - TruthfulQA MC | 50.08 | Accuracy (%) | 19.6 |
| Open Chinese LLM - WinoGrande | 60.22 | Accuracy (%) | 15 |
| Open Chinese LLM - HellaSwag | 53.21 | Accuracy (%) | 14.2 |
| Open Chinese LLM - ARC Challenge | 42.75 | Accuracy (%) | 10.5 |
| Open Chinese LLM - CMMLU | 41.55 | Accuracy (%) | 7.7 |
| Open Chinese LLM - C-Eval Semantic | 44.4 | Accuracy (%) | 7.1 |
Interactive version: theaggregate.ai/model?slug=unichat-llama3-chinese-8b-28k · How It Works · Data refreshed daily, snapshot 2026-09-23.