Updated March 25, 2026· Based on independent benchmark data
OpenAI: GPT-5.4 and Google: Gemini 3.1 Pro Preview are virtually tied on intelligence (57.2 vs 57.2). For speed, Google: Gemini 3.1 Pro Preview wins at 117 tok/s vs 77 tok/s.
| Metric | OpenAI: GPT-5.4 | Google: Gemini 3.1 Pro Preview |
|---|---|---|
| Intelligence Score | 57.2 | 57.2 |
| Coding Score | 57.3 | 55.5 |
| Math Score | N/A | N/A |
| Speed (tok/s) | 77 tok/s | 117 tok/s |
| Latency (TTFT) | 147.35s | 21.91s |
| Input Price / 1M tokens | $2.50 | $2.00 |
| Output Price / 1M tokens | $15 | $12 |
| Context Window | 1.1M |
OpenAI: GPT-5.4 and Google: Gemini 3.1 Pro Preview perform similarly on overall intelligence, scoring 57.2 and 57.2 respectively. Their coding capabilities are closely matched (57.3 vs 55.5).
Google: Gemini 3.1 Pro Preview generates output significantly faster at 117 tok/s compared to OpenAI: GPT-5.4's 77 tok/s, making it 1.5x faster for streaming responses. Time to first token is 21.91s for Google: Gemini 3.1 Pro Preview vs 147.35s for OpenAI: GPT-5.4, which affects perceived responsiveness in interactive applications.
Google: Gemini 3.1 Pro Preview is more affordable at $2.00/1M input tokens ($12/1M output), while OpenAI: GPT-5.4 costs $2.50/1M input ($15/1M output). For a typical workload of 100 requests per day at 2,000 tokens each, OpenAI: GPT-5.4 would cost approximately $15.00/month vs $12.00/month for Google: Gemini 3.1 Pro Preview in input costs alone.
OpenAI: GPT-5.4 offers a larger context window at 1.1M tokens compared to Google: Gemini 3.1 Pro Preview's 1.0M. For output length, OpenAI: GPT-5.4 can generate up to 128K tokens per response vs 66K for Google: Gemini 3.1 Pro Preview.
Choose Google: Gemini 3.1 Pro Preview when you need faster output (117 tok/s).
OpenAI: GPT-5.4 scores higher on coding benchmarks (57.3 vs 55.5), making it the better choice for programming tasks.
Google: Gemini 3.1 Pro Preview is cheaper at $2.00/1M input tokens vs $2.50/1M for OpenAI: GPT-5.4.
Google: Gemini 3.1 Pro Preview is faster, producing output at 117 tok/s compared to OpenAI: GPT-5.4's 77 tok/s.
Yes, OpenAI: GPT-5.4 supports image input. Google: Gemini 3.1 Pro Preview also supports images.
Data last synced: March 25, 2026
| 1.0M |
| Max Output Tokens | 128K | 66K |
| Input Modalities | Text + Image + File | Audio + File + Image + Text + Video |
| Output Modalities | Text | Text |
| Free Tier | No | No |
OpenAI: GPT-5.4 has a larger context window at 1.1M compared to Google: Gemini 3.1 Pro Preview's 1.0M.
Both models perform similarly on intelligence benchmarks. Choose based on specific needs: pricing, speed, context window, or provider ecosystem.