m1-32B-1k: benchmark results
Provider: Other.
Aggregate Rating 1578 ± 40, rank #1279 of 10916 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CureMed-Bench | 54.63 | Logical accuracy (%; share of final answers a GPT-4o judge m | 79.2 |
| EHRBench - MIMIC-IV | 65.49 | Accuracy (%) on the questions built from MIMIC-IV records, E | 70 |
| EHRBench - Prognosis | 51.73 | Accuracy (%) on the prognosis-decision questions (predict a | 70 |
| CureMed-Bench - Language Consistency | 48.92 | Language consistency (%; share of final answers written in t | 68.8 |
| EHRBench - Diagnosis | 63.07 | Accuracy (%) on the diagnosis-decision questions (complete a | 66.7 |
| EHRBench - PROMOTE | 61.46 | Accuracy (%) on the questions built from PROMOTE records, EH | 66.7 |
| EHRBench | 63.21 | Overall Acc (%) (self-reported) | 63.3 |
| EHRBench - MIMIC-III | 62.87 | Accuracy (%) on the questions built from MIMIC-III records, | 63.3 |
| EHRBench - Treatment | 74.84 | Accuracy (%) on the treatment-decision questions, EHR-ground | 63.3 |
Interactive version: theaggregate.ai/model?slug=m1-32b-1k · How It Works · Data refreshed daily, snapshot 2026-11-08.