Mirothinker 1.5 30B: benchmark results
Provider: Other.
Aggregate Rating 1544 ± 27, rank #1780 of 10916 rated models, from 28 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Medmarks - Med-HALT Reasoning NOTA | 59.98 | Score (%) | 60.2 |
| Medmarks - MetaMedQA | 65.87 | Score (%) | 47.7 |
| Medmarks - MedHallu Easy | 62.33 | Score (%) | 44.3 |
| Medmarks - MedHallu Medium | 55.03 | Score (%) | 43.2 |
| Medmarks - MedMCQA | 67.6 | Score (%) | 43.2 |
| Medmarks - MedHallu Hard | 43.15 | Score (%) | 42 |
| Medmarks - SuperGPQA Medicine Hard | 36.1 | Score (%) | 42 |
| Medmarks - SCTpublic | 63.72 | Score (%) | 40.9 |
| Medmarks - MedQA | 78.82 | Score (%) | 37.5 |
| Medmarks - SuperGPQA Medicine Easy | 47.12 | Score (%) | 36.4 |
| Medmarks - Med-HALT Reasoning FCT | 51.84 | Score (%) | 35.2 |
| Medmarks - MedXpertQA Reasoning | 19.51 | Score (%) | 35.2 |
Interactive version: theaggregate.ai/model?slug=mirothinker-1-5-30b · How It Works · Data refreshed daily, snapshot 2026-11-08.