system-one-bench

~/system-one-bench / compare/celeris-1-decision-vs-respan-span-02

Head to head

Celeris-1 Decision vs Span-02

Celeris-1 Decision scores 83.6 and Span-02 79.5 on the System One Index. Celeris-1 Decision is more accurate on 10 of 16 text datasets, Span-02 on 5, and 1 are tied. Same cases, same request, same scorer.

Overall

Celeris-1 DecisionSpan-02
System One Index83.679.5
English83.277.9
Arabic83.182.3
Vision Index–86.1
Calibration error2.6%10.5%
Median latency–204 ms
Cost per 1,000 calls$0.014$0.005

Text datasets, accuracy

Celeris-1 DecisionSpan-02
AG News English90.586.5
SST-2 English95.595.5
SST-5 English61.057.5
DAIR Emotion English72.556.0
Banking77 English89.082.0
BoolQ English89.590.0
XNLI English English91.383.3
Typed decisions English76.472.1
XNLI French French90.073.3
XNLI Arabic Arabic80.066.0
MASSIVE scenario Arabic73.571.0
MASSIVE intent Arabic88.086.0
OSACT4 offensive Arabic94.597.0
Tweet sentiment Arabic69.076.0
MIRACL rerank Arabic86.588.5
MIRACL pairwise Arabic90.091.5

Image datasets, accuracy

Celeris-1 DecisionSpan-02
SST-2, as an image–92.5
Arabic sentiment, as an image–70.0
Oxford-IIIT Pet–92.5
VQAv2 yes/no–87.0
CountBench–88.5

Model pages: Celeris-1 Decision · Span-02. Latency for API models is the median per call through OpenRouter, timed from a cloud server with 8 calls in flight.