benchgap
Other · model

Soofi S 30B-A3B benchmark scores

As of 2026-10-07, Soofi S 30B-A3B (Other) has measured scores on 3 benchmarks and estimated scores on 21 more.

BenchmarkScoreSource
AA-GPQA Diamond41.6%estimated ± 5.4 pp, medium confidence
AA-HLE0.0%estimated ± 4.0 pp, medium confidence
Artificial Analysis Intelligence Index10.3%estimated ± 6.2 pp, medium confidence
CritPt0.6%estimated ± 4.1 pp, high confidence
GPQA Diamond43.4%measured
HLE4.2%estimated ± 8.2 pp, low confidence
AA-Omniscience Accuracy16.2%estimated ± 8.1 pp, medium confidence
MMLU-Pro51.4%measured
GPQA43.4%measured
ARC-AGI-14.2%estimated ± 2.7 pp, medium confidence
ARC-AGI-26.7%estimated ± 10.1 pp, low confidence
Vals GPQA Diamond41.4%estimated ± 2.0 pp, medium confidence
Vals MMLU-Pro0.1%estimated ± 1.2 pp, medium confidence
HLE w/o tools5.7%estimated ± 4.4 pp, medium confidence
C-Eval59.2%estimated ± 0.9 pp, low confidence
MMLU-Redux71.9%estimated ± 0.7 pp, high confidence
SuperGPQA30.4%estimated ± 9.2 pp, low confidence
HealthBench Hard0.0%estimated ± 5.1 pp, low confidence
MedXpertQA (Text)8.5%estimated ± 4.5 pp, low confidence
MMLU-Pro (Arcee)63.1%estimated ± 3.4 pp, low confidence
ARC-AGI-30.0%estimated ± 2.1 pp, medium confidence
HealthBench Professional1.1%estimated ± 4.8 pp, low confidence
MMMLU15.9%estimated ± 1.1 pp, low confidence
MMLU68.9%estimated ± 3.6 pp, low confidence