GAMA: benchmark results

Provider: Other.

Aggregate Rating 1321 ± 46, rank #8292 of 10556 rated models, from 29 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMAU-Pro - Sound45.4Accuracy (%)76.5
MMAU-Pro - Multi-Audio20.2Accuracy (%)61.8
MedMosaic - Heart Sound MCQ36.6Accuracy (%; multiple choice, extracted answer letter agains45.8
MedMosaic - Lung Sound MCQ39.1Accuracy (%; multiple choice, extracted answer letter agains41.7
SonicBench - Texture62Accuracy (%; sound texture (ESC-50); 100 recognition and 10040.6
Afrispeech Semantics - Entailment (AfriSpeech-Medical)30.3Macro-F1 (%; three-way entailment, neutral or contradiction 40
MedMosaic - Cough Sound MCQ33.6Accuracy (%; multiple choice, extracted answer letter agains33.3
MedMosaic - Multi-Turn MCQ35Accuracy (%; multiple choice, extracted answer letter agains25
MMAU-Pro - Music41.2Accuracy (%)23.5
MMAU-Pro - Instruction Following31.7Accuracy (%)17.6
Afrispeech Semantics - Entailment (AfriSpeech-200)19.36Macro-F1 (%; three-way entailment, neutral or contradiction 16.7
Afrispeech Semantics - Plausibility (AfriSpeech-200)44.69Macro-F1 (%; plausible-but-unsupported versus implausible ju16.7

Interactive version: theaggregate.ai/model?slug=gama · How It Works · Data refreshed daily, snapshot 2026-11-17.