Lingshu-32B: benchmark results
Provider: Other. Released 2025-06-05. Access: Open.
Unified ELO 1644 ± 24, rank #477 of 2656 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Medical MM Leaderboard - Average | 66.6 | Average Accuracy (%) | 100 |
| Medical MM Leaderboard - OMVQA | 83.4 | Accuracy (%) | 100 |
| Medical MM Leaderboard - PathVQA | 65.9 | Accuracy (%) | 100 |
| Medical MM Leaderboard - SLAKE | 89.2 | Accuracy (%) | 100 |
| Medical MM Leaderboard - VQA-RAD | 76.5 | Accuracy (%) | 100 |
| Medical MM Leaderboard - PMC-VQA | 57.9 | Accuracy (%) | 90.5 |
| MedPIC-Bench - Rule Deactivation | 54.4 | Accuracy (%) | 85.2 |
| Medical MM Leaderboard - MedXQA | 30.9 | Accuracy (%) | 78.9 |
| MedPIC-Bench - Counterfactual | 53 | Accuracy (%) | 74.1 |
| Medical MM Leaderboard - MMMU-Med | 62.3 | Accuracy (%) | 71.4 |
| MedPIC-Bench - Counterfactual Pair | 25.8 | Both-correct pair rate (%) | 70.4 |
| CheXpercept | 89.9 | Stage 1 (End-to-End) (self-reported) | 69.2 |
Interactive version: theaggregate.ai/model?slug=lingshu-32b · How It Works · Data refreshed daily, snapshot 2026-09-19.