AntAngelMed 100B: benchmark results

Provider: Other.

Aggregate Rating 1623 ± 28, rank #801 of 10916 rated models, from 28 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Medmarks - SCTpublic74.05Score (%)93.2
Medmarks - Med-HALT Reasoning NOTA70.38Score (%)92
Medmarks - M-ARC60.33Score (%)80.1
Medmarks - MedHallu Medium63.61Score (%)75
Medmarks - MetaMedQA76.38Score (%)73.9
Medmarks - MedQA90Score (%)73.3
Medmarks - MMLU-Pro Health77.02Score (%)70.5
Medmarks - SuperGPQA Medicine Hard45.47Score (%)70.5
Medmarks - LongHealth Task 188.67Score (%)68.8
Medmarks - MedHallu Hard48.38Score (%)68.2
Medmarks - MedMCQA73.92Score (%)64.8
Medmarks - Med-HALT Reasoning FCT78.21Score (%)63.6

Interactive version: theaggregate.ai/model?slug=antangelmed-100b · How It Works · Data refreshed daily, snapshot 2026-11-08.