Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | GPT-4o (Aug '24) | Claude Sonnet 5 (Non-reasoning, High Effort) |
|---|---|---|
| Input ($/M tokens) | $2.5 | $2 |
| Output ($/M tokens) | $10 | $10 |
Data from Artificial Analysis API — 12 benchmarks
Claude Sonnet 5 (Non-reasoning, High Effort) is cheaper overall. Its blended price (3:1 input/output ratio) is $4.00/M tokens vs $4.38/M for GPT-4o (Aug '24).
Claude Sonnet 5 (Non-reasoning, High Effort) wins 5 out of 12 benchmarks compared to 4 for GPT-4o (Aug '24). See the detailed benchmark chart above for per-category results.
GPT-4o (Aug '24) generates tokens faster at 111 tok/s vs 0 tok/s. However, Claude Sonnet 5 (Non-reasoning, High Effort) has lower time-to-first-token (0.00s vs 0.63s).
Choose based on your priorities: Claude Sonnet 5 (Non-reasoning, High Effort) for lower cost, Claude Sonnet 5 (Non-reasoning, High Effort) for stronger benchmark performance, and GPT-4o (Aug '24) for faster generation. For latency-sensitive apps, check the TTFT comparison above.