Compare/Gemini 3 Pro Preview (low) vs GPT-5.3 Codex (xhigh)

Gemini 3 Pro Preview (low)vsGPT-5.3 Codex (xhigh)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Google

Gemini 3 Pro Preview (low)

Input
$2/M
Output
$12/M
Speed
110 tok/s
TTFT
3.62s
OpenAI

GPT-5.3 Codex (xhigh)

Input
$1.75/M
Output
$14/M
Speed
81 tok/s
TTFT
68.19s

Winner by Category

Cheaper
Gemini 3 Pro Preview (low)
Faster (tok/s)
Gemini 3 Pro Preview (low)
Lower Latency
Gemini 3 Pro Preview (low)
Benchmarks (4-7)
GPT-5.3 Codex (xhigh)

Pricing Comparison

MetricGemini 3 Pro Preview (low)GPT-5.3 Codex (xhigh)
Input ($/M tokens)$2$1.75
Output ($/M tokens)$12$14
Cost for 1M input + 100K output tokens:
Gemini 3 Pro Preview (low)$3.20
GPT-5.3 Codex (xhigh)$3.15

Speed Comparison

Output Speed (tokens/s) — higher is better
Gemini 3 Pro Preview (low)
110 tok/s
GPT-5.3 Codex (xhigh)
81 tok/s
Time to First Token (seconds) — lower is better
Gemini 3 Pro Preview (low)
3.62s
GPT-5.3 Codex (xhigh)
68.19s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
41.354.0
Coding Index
39.453.1
Math Index
86.7
GPQA Diamond
88.7%91.5%
MMLU-Pro
89.5%
LiveCodeBench
85.7%
AIME 2025
86.7%
MATH-500
Humanity's Last Exam
27.6%39.9%
SciCode
49.9%53.2%
IFBench
49.7%75.4%
TerminalBench
34.1%53.0%
Gemini 3 Pro Preview (low)4 wins
7 winsGPT-5.3 Codex (xhigh)

Frequently Asked Questions

Which is cheaper, Gemini 3 Pro Preview (low) or GPT-5.3 Codex (xhigh)?

Gemini 3 Pro Preview (low) 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).

Which model performs better on benchmarks?

GPT-5.3 Codex (xhigh) wins 7 out of 12 benchmarks compared to 4 for Gemini 3 Pro Preview (low). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Gemini 3 Pro Preview (low) generates tokens faster at 110 tok/s vs 81 tok/s. Gemini 3 Pro Preview (low) also has lower time-to-first-token (3.62s vs 68.19s).

When should I use Gemini 3 Pro Preview (low) vs GPT-5.3 Codex (xhigh)?

Choose based on your priorities: Gemini 3 Pro Preview (low) for lower cost, GPT-5.3 Codex (xhigh) for stronger benchmark performance, and Gemini 3 Pro Preview (low) for faster generation. For latency-sensitive apps, check the TTFT comparison above.