Verdict
Built from the measurements below
- Accuracy is too close to call: Phi 4 scored 41.2% and Solar Mini 4 41.2% on the same 80 questions, a gap within what chance alone could produce.
- Phi 4 is 4.4× cheaper per question as billed ($0.00012 vs $0.00053), reasoning tokens included.
- Output speed is similar (103 vs 107 tokens per second).
- Phi 4 starts answering sooner: 0.5 s to the first token, against 0.7 s for Solar Mini 4.
- Solar Mini 4 accepts more context: 524k tokens against 16k.
Which should you choose?
Choose Phi 4 for the lower cost per correct answer ($0.00029 against $0.0013), a quicker first token, shorter outputs (about 699 tokens per question against 2,552) and open weights you can run yourself. Choose Solar Mini 4 for a 524k-token context window. The widest subject gap is in law: Phi 4 answered 2 of 6 correctly, Solar Mini 4 0 of 6. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.
Accuracy gap +0.0 points (z = 0.00). We call a winner only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.