Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Claude 3.5 Sonnet (Oct '24) | GPT-5.4 (low) |
|---|---|---|
| Input ($/M tokens) | $3.75 | $2.5 |
| Output ($/M tokens) | $15 | $15 |
Data from Artificial Analysis API — 12 benchmarks
GPT-5.4 (low) is cheaper overall. Its blended price (3:1 input/output ratio) is $5.63/M tokens vs $6.56/M for Claude 3.5 Sonnet (Oct '24).
GPT-5.4 (low) wins 7 out of 12 benchmarks compared to 3 for Claude 3.5 Sonnet (Oct '24). See the detailed benchmark chart above for per-category results.
GPT-5.4 (low) generates tokens faster at 64 tok/s vs 0 tok/s. Claude 3.5 Sonnet (Oct '24) also has lower time-to-first-token (0.00s vs 1.61s).
Choose based on your priorities: GPT-5.4 (low) for lower cost, GPT-5.4 (low) for stronger benchmark performance, and GPT-5.4 (low) for faster generation. For latency-sensitive apps, check the TTFT comparison above.