Verdict
Built from the measurements below
- Accuracy is too close to call: DeepSeek V4 Pro 0813 scored 71.2% and o3 72.5% on the same 80 questions, a gap within what chance alone could produce.
- DeepSeek V4 Pro 0813 is 2.4× cheaper per question as billed ($0.0036 vs $0.0088), reasoning tokens included.
- o3 generates text 2.9× faster: 163 tokens per second against 56.
- DeepSeek V4 Pro 0813 starts answering sooner: 0.8 s to the first token, against 1.2 s for o3.
- DeepSeek V4 Pro 0813 accepts more context: 1M tokens against 200k.
Which should you choose?
Choose DeepSeek V4 Pro 0813 for the lower cost per correct answer ($0.0051 against $0.012), a quicker first token, open weights you can run yourself, a 1M-token context window and more hosts to choose from on OpenRouter (23 against 1). Choose o3 for faster streaming. The widest subject gap is in medicine: o3 answered 7 of 11 correctly, DeepSeek V4 Pro 0813 4 of 11. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.
Accuracy gap -1.2 points (z = -0.18). We call a winner only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.