PlatYi-34B-Llama-Q-v3: benchmark results
Provider: kyujinpy. Access: Open.
Aggregate Rating 1469 ± 41, rank #2858 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 74.98 | Accuracy (%) (5-shot) | 96.4 |
| Open LLM Leaderboard v1 - WinoGrande | 84.21 | Accuracy (%) (5-shot) | 92.4 |
| Open LLM Leaderboard v1 - HellaSwag | 84.88 | Normalized accuracy (%) (10-shot) | 69.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 64.33 | Normalized accuracy (%) (25-shot) | 66.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.8 | MC2 (%) (0-shot) | 53.3 |
| Open LLM Leaderboard v1 - GSM8K | 6.67 | Accuracy (%) (5-shot) | 25.8 |
Interactive version: theaggregate.ai/model?slug=platyi-34b-llama-q-v3 · How It Works · Data refreshed daily, snapshot 2026-11-08.