Updated March 26, 2026· Based on independent benchmark data
GPT-5.4 mini (xhigh) and Gemini 3 Flash Preview (Reasoning) are virtually tied on intelligence (48.1 vs 46.4).
| Metric | GPT-5.4 mini (xhigh) | Gemini 3 Flash Preview (Reasoning) |
|---|---|---|
| Intelligence Score | 48.1 | 46.4 |
| Coding Score | 51.5 | 42.6 |
| Math Score | N/A | 97.0 |
| Speed (tok/s) | 218 tok/s | 192 tok/s |
| Latency (TTFT) | 7.45s | 6.11s |
| Input Price / 1M tokens | $0.75 | $0.50 |
| Output Price / 1M tokens | $4.50 | $3.00 |
| Context Window | N/A |
GPT-5.4 mini (xhigh) and Gemini 3 Flash Preview (Reasoning) perform similarly on overall intelligence, scoring 48.1 and 46.4 respectively. For coding tasks, GPT-5.4 mini (xhigh) has the edge with a coding score of 51.5 vs 42.6.
Both models deliver similar output speeds: GPT-5.4 mini (xhigh) at 218 tok/s and Gemini 3 Flash Preview (Reasoning) at 192 tok/s. Time to first token is 6.11s for Gemini 3 Flash Preview (Reasoning) vs 7.45s for GPT-5.4 mini (xhigh), which affects perceived responsiveness in interactive applications.
Gemini 3 Flash Preview (Reasoning) is more affordable at $0.50/1M input tokens ($3.00/1M output), while GPT-5.4 mini (xhigh) costs $0.75/1M input ($4.50/1M output). For a typical workload of 100 requests per day at 2,000 tokens each, GPT-5.4 mini (xhigh) would cost approximately $4.50/month vs $3.00/month for Gemini 3 Flash Preview (Reasoning) in input costs alone.
Choose GPT-5.4 mini (xhigh) when you need stronger coding performance (51.5).
GPT-5.4 mini (xhigh) scores higher on coding benchmarks (51.5 vs 42.6), making it the better choice for programming tasks.
Gemini 3 Flash Preview (Reasoning) is cheaper at $0.50/1M input tokens vs $0.75/1M for GPT-5.4 mini (xhigh).
GPT-5.4 mini (xhigh) is faster, producing output at 218 tok/s compared to Gemini 3 Flash Preview (Reasoning)'s 192 tok/s.
No, GPT-5.4 mini (xhigh) does not support image input. Neither model supports image input.
Data last synced: March 26, 2026
| N/A |
| Max Output Tokens | N/A | N/A |
| Input Modalities | Text | Text |
| Output Modalities | Text | Text |
| Free Tier | No | No |
Both models perform similarly on intelligence benchmarks. Choose based on specific needs: pricing, speed, context window, or provider ecosystem.