vicuna-7B-v1.3-attention-sparsity-20: benchmark results
Provider: LMSYS. Access: Open.
Aggregate Rating 1301 ± 33, rank #8715 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.62 | MC2 (%) (0-shot) | 35 |
| Open LLM Leaderboard v1 - GSM8K | 11.22 | Accuracy (%) (5-shot) | 32.5 |
| Open LLM Leaderboard v1 - HellaSwag | 77.05 | Normalized accuracy (%) (10-shot) | 30 |
| Open LLM Leaderboard v1 - ARC Challenge | 52.3 | Normalized accuracy (%) (25-shot) | 26.9 |
| Open LLM Leaderboard v1 - MMLU | 47.39 | Accuracy (%) (5-shot) | 26.2 |
| Open LLM Leaderboard v1 - WinoGrande | 69.22 | Accuracy (%) (5-shot) | 23.3 |
Interactive version: theaggregate.ai/model?slug=vicuna-7b-v1-3-attention-sparsity-20 · How It Works · Data refreshed daily, snapshot 2026-11-08.