vicuna-7B-v1.3-sparsity-10: benchmark results
Provider: LMSYS. Access: Open.
Aggregate Rating 1304 ± 33, rank #8665 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.88 | MC2 (%) (0-shot) | 35.8 |
| Open LLM Leaderboard v1 - GSM8K | 13.12 | Accuracy (%) (5-shot) | 35 |
| Open LLM Leaderboard v1 - HellaSwag | 76.98 | Normalized accuracy (%) (10-shot) | 29.9 |
| Open LLM Leaderboard v1 - MMLU | 47.95 | Accuracy (%) (5-shot) | 27 |
| Open LLM Leaderboard v1 - ARC Challenge | 51.45 | Normalized accuracy (%) (25-shot) | 25.9 |
| Open LLM Leaderboard v1 - WinoGrande | 69.77 | Accuracy (%) (5-shot) | 24 |
Interactive version: theaggregate.ai/model?slug=vicuna-7b-v1-3-sparsity-10 · How It Works · Data refreshed daily, snapshot 2026-11-08.