HuaTuoGPT-Vision-34B: benchmark results
Provider: Other.
Aggregate Rating 1542 ± 38, rank #1808 of 10916 rated models, from 22 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| DrVD-Bench | 66 | Overall Accuracy (%) | 94.4 |
| Med-R2 - Anatomy Level | 65.9 | Accuracy (%) on the Med-R2 Anatomy Level task (locating and | 92.3 |
| Med-R2 - Lesion Level | 53.5 | Accuracy (%) on the Med-R2 Lesion Level task (detecting and | 61.5 |
| X-PCR - Clinical Decision-Making | 40.64 | Accuracy (%) at stage 6, choosing management (items written | 55 |
| Med-R2 | 55.6 | Overall average accuracy (%) over the Image Quality, Anatomy | 53.8 |
| Med-R2 - Image Quality | 48 | Accuracy (%) on the Med-R2 Image Quality task (judging the q | 38.5 |
| CareQA-Vision - MCQ - Nursing | 47.62 | Accuracy (%; 42 image-based multiple-choice questions from E | 38.2 |
| X-PCR - Anatomical Localization | 66.01 | Accuracy (%) at stage 2, locating key fundus structures, on | 35 |
| X-PCR - Severity Grading | 47.59 | Accuracy (%) at stage 5, grading disease severity, on X-PCR' | 35 |
| X-PCR - Specialist-Level Questions | 41.95 | Accuracy (%) on the questions ophthalmologists rated at spec | 35 |
| Med-R2 - Joint QA | 54.8 | Accuracy (%) on the Med-R2 Joint QA task (answering all reas | 30.8 |
| X-PCR | 57.37 | Stage-wise accuracy (%) averaged over the six stages of the | 30 |
Interactive version: theaggregate.ai/model?slug=huatuogpt-vision-34b · How It Works · Data refreshed daily, snapshot 2026-11-08.