vicuna-7B-v1.3 — benchmark results
Provider: LMSYS. Released 2023-06-18. Access: Open.
Unified ELO 1171 ± 32, rank #1717 of 1776 rated models, from 85 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Mathematics | 36 | Accuracy (%) | 80.3 |
| LLM Trustworthy - Adversarial | 52.16 | Trust Score (%) | 80 |
| MMLU-by-task - High School Statistics | 45.83 | Accuracy (%) | 77 |
| MMLU-by-task - Elementary Mathematics | 32.54 | Accuracy (%) | 70.2 |
| MMLU-by-task - Jurisprudence | 66.67 | Accuracy (%) | 68.1 |
| MMLU-by-task - College Computer Science | 44 | Accuracy (%) | 67.5 |
| MMLU-by-task - Formal Logic | 34.13 | Accuracy (%) | 66.1 |
| MMLU-by-task - Medical Genetics | 56 | Accuracy (%) | 65.2 |
| MMLU-by-task - TruthfulQA MC1 | 31.7 | Accuracy (%) | 65.2 |
| MMLU-by-task - International Law | 67.77 | Accuracy (%) | 63.3 |
| MMLU-by-task - High School Macroeconomics | 47.69 | Accuracy (%) | 62.9 |
| MMLU-by-task - Sociology | 67.66 | Accuracy (%) | 62.1 |
Interactive version: theaggregate.ai/model?slug=vicuna-7b-v1-3 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.