system-one-bench

~/system-one-bench / compare/patrick-18-dexy-decision-9b-vs-vllm-semantic-router-d3-nano

Head to head

Dexy-Decision-9B vs d3 nano

Dexy-Decision-9B scores 84.7 and d3 nano 78.0 on the System One Index. Dexy-Decision-9B is more accurate on 13 of 16 text datasets, d3 nano on 2, and 1 are tied. Same cases, same request, same scorer.

Overall

Dexy-Decision-9Bd3 nano
System One Index84.778.0
English82.377.9
Arabic86.876.9
Vision Index––
Calibration error3.5%7.0%
Median latency––
Cost per 1,000 calls––

Text datasets, accuracy

Dexy-Decision-9Bd3 nano
AG News English91.588.0
SST-2 English95.589.5
SST-5 English60.055.5
DAIR Emotion English54.059.5
Banking77 English93.093.0
BoolQ English89.588.0
XNLI English English94.787.3
Typed decisions English80.062.6
XNLI French French89.386.0
XNLI Arabic Arabic89.382.0
MASSIVE scenario Arabic89.561.5
MASSIVE intent Arabic91.581.0
OSACT4 offensive Arabic91.579.0
Tweet sentiment Arabic67.071.0
MIRACL rerank Arabic88.077.5
MIRACL pairwise Arabic91.086.5

Model pages: Dexy-Decision-9B · d3 nano. Latency for API models is the median per call through OpenRouter, timed from a cloud server with 8 calls in flight.