Verdict
Built from the measurements below
- Accuracy is too close to call: Inkling scored 66.2% and Inkling Small 67.5% on the same 80 questions, a gap within what chance alone could produce.
- Inkling Small is 2.6× cheaper per question as billed ($0.00047 vs $0.0012), reasoning tokens included.
- Inkling Small generates text 2.0× faster: 233 tokens per second against 118.
Which should you choose?
Choose Inkling Small for the lower cost per correct answer ($0.00069 against $0.0019) and faster streaming.
Accuracy gap -1.3 points (z = -0.17). We call a winner only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.