Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | GPT-5.6 Terra (Non-reasoning) | Claude Sonnet 4.6 (Non-reasoning, Low Effort) |
|---|---|---|
| Input ($/M tokens) | $2.5 | $3 |
| Output ($/M tokens) | $15 | $15 |
Data from Artificial Analysis API — 12 benchmarks
GPT-5.6 Terra (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $5.63/M tokens vs $6.00/M for Claude Sonnet 4.6 (Non-reasoning, Low Effort).
Claude Sonnet 4.6 (Non-reasoning, Low Effort) wins 4 out of 12 benchmarks compared to 3 for GPT-5.6 Terra (Non-reasoning). See the detailed benchmark chart above for per-category results.
GPT-5.6 Terra (Non-reasoning) generates tokens faster at 146 tok/s vs 51 tok/s. GPT-5.6 Terra (Non-reasoning) also has lower time-to-first-token (0.76s vs 1.03s).
Choose based on your priorities: GPT-5.6 Terra (Non-reasoning) for lower cost, Claude Sonnet 4.6 (Non-reasoning, Low Effort) for stronger benchmark performance, and GPT-5.6 Terra (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.