yi6B_Vicuna: benchmark results
Provider: 01.AI. Access: Open.
Aggregate Rating 1328 ± 42, rank #8206 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 58.43 | Accuracy (%) (5-shot) | 43.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 48.11 | MC2 (%) (0-shot) | 39.9 |
| Open LLM Leaderboard v1 - GSM8K | 18.42 | Accuracy (%) (5-shot) | 39.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 46.16 | Normalized accuracy (%) (25-shot) | 21.3 |
| Open LLM Leaderboard v1 - HellaSwag | 69.3 | Normalized accuracy (%) (10-shot) | 19.9 |
| Open LLM Leaderboard v1 - WinoGrande | 65.67 | Accuracy (%) (5-shot) | 19.2 |
Interactive version: theaggregate.ai/model?slug=yi6b-vicuna · How It Works · Data refreshed daily, snapshot 2026-11-08.