vicuna-7B-v1.5 — benchmark results
Provider: LMSYS. Released 2023-07-29. Access: Open.
Unified ELO 1222 ± 17, rank #1660 of 1776 rated models, from 100 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Mathematics | 39 | Accuracy (%) | 92.7 |
| MMLU-by-task - Machine Learning | 44.64 | Accuracy (%) | 88.1 |
| MMLU-by-task - Formal Logic | 38.1 | Accuracy (%) | 82 |
| MMLU-by-task - Anatomy | 50.37 | Accuracy (%) | 79.5 |
| MMLU-by-task - TruthfulQA MC2 | 50.34 | Accuracy (%) | 77.6 |
| MMLU-by-task - Professional Medicine | 54.04 | Accuracy (%) | 77 |
| MMLU-by-task - Security Studies | 62.86 | Accuracy (%) | 76.6 |
| MMLU-by-task - Human Sexuality | 63.36 | Accuracy (%) | 76.3 |
| MMLU-by-task - Conceptual Physics | 45.11 | Accuracy (%) | 75.8 |
| MMLU-by-task - TruthfulQA MC1 | 33.17 | Accuracy (%) | 71.6 |
| MMLU-by-task - Public Relations | 61.82 | Accuracy (%) | 71.3 |
| MMLU-by-task - Business Ethics | 54 | Accuracy (%) | 70.7 |
Interactive version: theaggregate.ai/model?slug=vicuna-7b-v1-5 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.