PlatYi-34B-Q: benchmark results
Rank-16 QLoRA experiment on original Yi-34B and Open-Platypus. Q denotes training method, not proof of quantized release storage. Provider: kyujinpy. Access: Open.
Aggregate Rating 1488 ± 38, rank #2547 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 77.66 | Accuracy (%) (5-shot) | 98.9 |
| Open LLM Leaderboard v1 - WinoGrande | 82.48 | Accuracy (%) (5-shot) | 84.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 66.89 | Normalized accuracy (%) (25-shot) | 75.1 |
| Open LLM Leaderboard v1 - HellaSwag | 85.14 | Normalized accuracy (%) (10-shot) | 72.1 |
| Open LLM Leaderboard v1 - GSM8K | 53.98 | Accuracy (%) (5-shot) | 65.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 53.03 | MC2 (%) (0-shot) | 58.2 |
Interactive version: theaggregate.ai/model?slug=platyi-34b-q · How It Works · Data refreshed daily, snapshot 2026-11-08.