CantoneseLLMChat-preview20240326: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1346 ± 37, rank #7800 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 59.19 | Accuracy (%) (5-shot) | 44.8 |
| Open LLM Leaderboard v1 - GSM8K | 25.63 | Accuracy (%) (5-shot) | 44.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 52.56 | Normalized accuracy (%) (25-shot) | 27.4 |
| Open LLM Leaderboard v1 - WinoGrande | 70.32 | Accuracy (%) (5-shot) | 24.7 |
| Open LLM Leaderboard v1 - HellaSwag | 69.05 | Normalized accuracy (%) (10-shot) | 19.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.87 | MC2 (%) (0-shot) | 18.6 |
Interactive version: theaggregate.ai/model?slug=cantonesellmchat-preview20240326 · How It Works · Data refreshed daily, snapshot 2026-11-08.