Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Gemini 3.1 Pro Preview | GPT-5.3 Codex (xhigh) |
|---|---|---|
| Input ($/M tokens) | $2 | $1.75 |
| Output ($/M tokens) | $12 | $14 |
Data from Artificial Analysis API — 12 benchmarks
Gemini 3.1 Pro Preview is cheaper overall. Its blended price (3:1 input/output ratio) is $4.50/M tokens vs $4.81/M for GPT-5.3 Codex (xhigh).
Gemini 3.1 Pro Preview wins 7 out of 12 benchmarks compared to 0 for GPT-5.3 Codex (xhigh). See the detailed benchmark chart above for per-category results.
Gemini 3.1 Pro Preview generates tokens faster at 115 tok/s vs 81 tok/s. Gemini 3.1 Pro Preview also has lower time-to-first-token (31.49s vs 68.19s).
Choose based on your priorities: Gemini 3.1 Pro Preview for lower cost, Gemini 3.1 Pro Preview for stronger benchmark performance, and Gemini 3.1 Pro Preview for faster generation. For latency-sensitive apps, check the TTFT comparison above.