Updated March 25, 2026· Based on independent benchmark data
OpenAI: GPT-5.4 leads in intelligence with a score of 57.2 vs 51.7.
| Metric | OpenAI: GPT-5.4 | Anthropic: Claude Sonnet 4 |
|---|---|---|
| Intelligence Score | 57.2 | 51.7 |
| Coding Score | 57.3 | 50.9 |
| Math Score | N/A | N/A |
| Speed (tok/s) | 77 tok/s | 65 tok/s |
| Latency (TTFT) | 147.35s | 38.68s |
| Input Price / 1M tokens | $2.50 | $3.00 |
| Output Price / 1M tokens | $15 | $15 |
| Context Window | 1.1M |
OpenAI: GPT-5.4 outperforms Anthropic: Claude Sonnet 4 on the Artificial Analysis intelligence index with a score of 57.2 compared to 51.7. For coding tasks, OpenAI: GPT-5.4 has the edge with a coding score of 57.3 vs 50.9.
Both models deliver similar output speeds: OpenAI: GPT-5.4 at 77 tok/s and Anthropic: Claude Sonnet 4 at 65 tok/s. Time to first token is 38.68s for Anthropic: Claude Sonnet 4 vs 147.35s for OpenAI: GPT-5.4, which affects perceived responsiveness in interactive applications.
OpenAI: GPT-5.4 is more affordable at $2.50/1M input tokens ($15/1M output), while Anthropic: Claude Sonnet 4 costs $3.00/1M 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 $18.00/month for Anthropic: Claude Sonnet 4 in input costs alone.
OpenAI: GPT-5.4 offers a larger context window at 1.1M tokens compared to Anthropic: Claude Sonnet 4's 200K. This means OpenAI: GPT-5.4 can process roughly 525 pages of text in a single request vs 100 pages for Anthropic: Claude Sonnet 4. For output length, OpenAI: GPT-5.4 can generate up to 128K tokens per response vs 64K for Anthropic: Claude Sonnet 4.
Choose OpenAI: GPT-5.4 when you need higher intelligence (57.2), stronger coding performance (57.3), larger context window (1.1M).
OpenAI: GPT-5.4 scores higher on coding benchmarks (57.3 vs 50.9), making it the better choice for programming tasks.
OpenAI: GPT-5.4 is cheaper at $2.50/1M input tokens vs $3.00/1M for Anthropic: Claude Sonnet 4.
OpenAI: GPT-5.4 is faster, producing output at 77 tok/s compared to Anthropic: Claude Sonnet 4's 65 tok/s.
Yes, OpenAI: GPT-5.4 supports image input. Anthropic: Claude Sonnet 4 also supports images.
Benchmark data by Artificial Analysis
Data last synced: March 25, 2026
| 200K |
| Max Output Tokens | 128K | 64K |
| Input Modalities | Text + Image + File | Image + Text + File |
| Output Modalities | Text | Text |
| Free Tier | No | No |
OpenAI: GPT-5.4 has a larger context window at 1.1M compared to Anthropic: Claude Sonnet 4's 200K.
It depends on your priorities. OpenAI: GPT-5.4 scores higher on intelligence (57.2), but Anthropic: Claude Sonnet 4 may be better for specific use cases like budget-conscious projects or speed-critical applications.