Updated March 26, 2026· Based on independent benchmark data
GPT-5.4 (xhigh) leads in intelligence with a score of 57.2 vs 19.0.
| Metric | Nova Premier | GPT-5.4 (xhigh) |
|---|---|---|
| Intelligence Score | 19.0 | 57.2 |
| Coding Score | 13.8 | 57.3 |
| Math Score | 17.3 | N/A |
| Speed (tok/s) | 65 tok/s | 77 tok/s |
| Latency (TTFT) | 0.88s | 181.82s |
| Input Price / 1M tokens | $2.50 | $2.50 |
| Output Price / 1M tokens | $13 | $15 |
| Context Window | 1M | N/A |
| Max Output Tokens | N/A | N/A |
| Input Modalities | Text + Image | Text |
GPT-5.4 (xhigh) outperforms Nova Premier on the intelligence index with a score of 57.2 compared to 19.0. For coding tasks, GPT-5.4 (xhigh) has the edge with a coding score of 57.3 vs 13.8.
Both models deliver similar output speeds: Nova Premier at 65 tok/s and GPT-5.4 (xhigh) at 77 tok/s. Time to first token is 0.88s for Nova Premier vs 181.82s for GPT-5.4 (xhigh), which affects perceived responsiveness in interactive applications.
GPT-5.4 (xhigh) is more affordable at $2.50/1M input tokens ($15/1M output), while Nova Premier costs $2.50/1M input ($13/1M output). For a typical workload of 100 requests per day at 2,000 tokens each, Nova Premier would cost approximately $15.00/month vs $15.00/month for GPT-5.4 (xhigh) in input costs alone.
Choose GPT-5.4 (xhigh) when you need higher intelligence (57.2), stronger coding performance (57.3).
GPT-5.4 (xhigh) scores higher on coding benchmarks (57.3 vs 13.8), making it the better choice for programming tasks.
GPT-5.4 (xhigh) is cheaper at $2.50/1M input tokens vs $2.50/1M for Nova Premier.
GPT-5.4 (xhigh) is faster, producing output at 77 tok/s compared to Nova Premier's 65 tok/s.
Yes, Nova Premier supports image input. GPT-5.4 (xhigh) does not support image input.
Data last synced: March 26, 2026
| Output Modalities |
| Text |
| Text |
| Free Tier | No | No |
It depends on your priorities. GPT-5.4 (xhigh) scores higher on intelligence (57.2), but Nova Premier may be better for specific use cases like budget-conscious projects or speed-critical applications.