DASD 30B-A3B: benchmark results

Provider: Other.

Aggregate Rating 1564 ± 36, rank #1493 of 10916 rated models, from 28 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Medmarks - MedHallu Medium63.31Score (%)72.7
Medmarks - MedHallu Easy67.43Score (%)60.2
Medmarks - MetaMedQA72.15Score (%)56.8
Medmarks - LongHealth Task 187.75Score (%)55.1
Medmarks - MedHallu Hard46.06Score (%)53.4
Medmarks - SuperGPQA Medicine Easy53.91Score (%)51.1
Medmarks - Medbullets OP475.43Score (%)46.6
Medmarks - SuperGPQA Medicine Hard37.63Score (%)45.5
Medmarks - M-ARC34.33Score (%)43.2
Medmarks - LongHealth Task 286.88Score (%)41.5
Medmarks - Medbullets OP567.97Score (%)41.5
Medmarks - Med-HALT Reasoning FCT57.72Score (%)39.8

Interactive version: theaggregate.ai/model?slug=dasd-30b-a3b · How It Works · Data refreshed daily, snapshot 2026-11-08.