Updated March 25, 2026· Based on independent benchmark data
OpenAI: GPT-5.2-Codex leads in intelligence with a score of 54.0 vs 48.4. For speed, Google: Nano Banana Pro (Gemini 3 Pro Image Preview) wins at 119 tok/s vs 68 tok/s.
| Metric | OpenAI: GPT-5.2-Codex | Google: Nano Banana Pro (Gemini 3 Pro Image Preview) |
|---|---|---|
| Intelligence Score | 54.0 | 48.4 |
| Coding Score | 53.1 | 46.5 |
| Math Score | N/A | 95.7 |
| Speed (tok/s) | 68 tok/s | 119 tok/s |
| Latency (TTFT) | 75.14s | 21.66s |
| Input Price / 1M tokens | $1.75 | $2.00 |
| Output Price / 1M tokens | $14 | $12 |
| Context Window | 400K |
OpenAI: GPT-5.2-Codex outperforms Google: Nano Banana Pro (Gemini 3 Pro Image Preview) on the Artificial Analysis intelligence index with a score of 54.0 compared to 48.4. For coding tasks, OpenAI: GPT-5.2-Codex has the edge with a coding score of 53.1 vs 46.5.
Google: Nano Banana Pro (Gemini 3 Pro Image Preview) generates output significantly faster at 119 tok/s compared to OpenAI: GPT-5.2-Codex's 68 tok/s, making it 1.8x faster for streaming responses. Time to first token is 21.66s for Google: Nano Banana Pro (Gemini 3 Pro Image Preview) vs 75.14s for OpenAI: GPT-5.2-Codex, which affects perceived responsiveness in interactive applications.
OpenAI: GPT-5.2-Codex is more affordable at $1.75/1M input tokens ($14/1M output), while Google: Nano Banana Pro (Gemini 3 Pro Image Preview) costs $2.00/1M input ($12/1M output). For a typical workload of 100 requests per day at 2,000 tokens each, OpenAI: GPT-5.2-Codex would cost approximately $10.50/month vs $12.00/month for Google: Nano Banana Pro (Gemini 3 Pro Image Preview) in input costs alone.
OpenAI: GPT-5.2-Codex offers a larger context window at 400K tokens compared to Google: Nano Banana Pro (Gemini 3 Pro Image Preview)'s 66K. This means OpenAI: GPT-5.2-Codex can process roughly 200 pages of text in a single request vs 33 pages for Google: Nano Banana Pro (Gemini 3 Pro Image Preview). For output length, OpenAI: GPT-5.2-Codex can generate up to 128K tokens per response vs 33K for Google: Nano Banana Pro (Gemini 3 Pro Image Preview).
Choose OpenAI: GPT-5.2-Codex when you need higher intelligence (54.0), stronger coding performance (53.1), larger context window (400K). Choose Google: Nano Banana Pro (Gemini 3 Pro Image Preview) when you need faster output (119 tok/s).
OpenAI: GPT-5.2-Codex scores higher on coding benchmarks (53.1 vs 46.5), making it the better choice for programming tasks.
OpenAI: GPT-5.2-Codex is cheaper at $1.75/1M input tokens vs $2.00/1M for Google: Nano Banana Pro (Gemini 3 Pro Image Preview).
Google: Nano Banana Pro (Gemini 3 Pro Image Preview) is faster, producing output at 119 tok/s compared to OpenAI: GPT-5.2-Codex's 68 tok/s.
Yes, OpenAI: GPT-5.2-Codex supports image input. Google: Nano Banana Pro (Gemini 3 Pro Image Preview) also supports images.
Benchmark data by Artificial Analysis
Data last synced: March 25, 2026
| 66K |
| Max Output Tokens | 128K | 33K |
| Input Modalities | Text + Image | Image + Text |
| Output Modalities | Text | Image + Text |
| Free Tier | No | No |
OpenAI: GPT-5.2-Codex has a larger context window at 400K compared to Google: Nano Banana Pro (Gemini 3 Pro Image Preview)'s 66K.
It depends on your priorities. OpenAI: GPT-5.2-Codex scores higher on intelligence (54.0), but Google: Nano Banana Pro (Gemini 3 Pro Image Preview) may be better for specific use cases like budget-conscious projects or speed-critical applications.