HealthGPT-L14B: benchmark results
Provider: Other.
Aggregate Rating 1566 ± 42, rank #1458 of 10916 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MedQ-Deg - Diagnostic Reasoning | 40.9 | Accuracy (%) on the Diagnosis questions of MedQ-Deg (capabil | 87.2 |
| MedQ-Deg - Imaging Perception | 33 | Accuracy (%) on the Imaging Perception questions of MedQ-Deg | 80.8 |
| MedQ-Deg - Clinical Understanding | 66.6 | Accuracy (%) on the Clinical Understanding questions of MedQ | 66.7 |
| MedQ-Deg - Artifact Degradation | 55.3 | Accuracy (%) on MedQ-Deg items whose images carry imaging-ar | 51.3 |
| MedQ-Deg - Mild Degradation (L1) | 59.71 | Accuracy (%) on the MedQ-Deg items with mild degradations (L | 51.3 |
| MedQ-Deg - Resolution and Blur Degradation | 59.5 | Accuracy (%) on MedQ-Deg items whose images carry resolution | 51.3 |
| MedQ-Deg - Severe Degradation (L2) | 56.75 | Accuracy (%) on the MedQ-Deg items with severe degradations | 51.3 |
| MedQ-Deg - Clean (L0) | 60.29 | Accuracy (%) on the MedQ-Deg items with the original, undegr | 48.7 |
| MedQ-Deg - Motion Degradation | 58.8 | Accuracy (%) on MedQ-Deg items whose images carry motion-int | 48.7 |
| MedQ-Deg - Noise Degradation | 57 | Accuracy (%) on MedQ-Deg items whose images carry noise degr | 48.7 |
| MedQ-Deg - Intensity Degradation | 63.5 | Accuracy (%) on MedQ-Deg items whose images carry intensity- | 46.2 |
| MMRareBench - Treatment Planning | 14.1 | Treatment Planning track (T2) score: a stage-wise treatment | 45.5 |
Interactive version: theaggregate.ai/model?slug=healthgpt-l14b · How It Works · Data refreshed daily, snapshot 2026-11-08.