Verdict
Built from the measurements below
- Accuracy is too close to call: Gemini 3.8 Flash scored 82.5% and GPT-5.3-Codex 82.5% on the same 80 questions, a gap within what chance alone could produce.
- Gemini 3.8 Flash is 2.8× cheaper per question as billed ($0.0037 vs $0.01), reasoning tokens included.
- Gemini 3.8 Flash generates text 1.5× faster: 142 tokens per second against 95.
- GPT-5.3-Codex starts answering sooner: 1.4 s to the first token, against 3.2 s for Gemini 3.8 Flash.
- Gemini 3.8 Flash accepts more context: 1M tokens against 400k.
Which should you choose?
Choose Gemini 3.8 Flash for the lower cost per correct answer ($0.0045 against $0.013), faster streaming and a 1M-token context window. Choose GPT-5.3-Codex for a quicker first token. The widest subject gap is in law: Gemini 3.8 Flash answered 6 of 6 correctly, GPT-5.3-Codex 4 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.