Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Claude 4 Sonnet (Non-reasoning) | Grok 3 |
|---|---|---|
| Input ($/M tokens) | $3.75 | $3 |
| Output ($/M tokens) | $15 | $15 |
Data from Artificial Analysis API — 12 benchmarks
Grok 3 is cheaper overall. Its blended price (3:1 input/output ratio) is $6.00/M tokens vs $6.56/M for Claude 4 Sonnet (Non-reasoning).
Claude 4 Sonnet (Non-reasoning) wins 7 out of 12 benchmarks compared to 5 for Grok 3. See the detailed benchmark chart above for per-category results.
Claude 4 Sonnet (Non-reasoning) generates tokens faster at 53 tok/s vs 37 tok/s. However, Grok 3 has lower time-to-first-token (0.65s vs 0.94s).
Choose based on your priorities: Grok 3 for lower cost, Claude 4 Sonnet (Non-reasoning) for stronger benchmark performance, and Claude 4 Sonnet (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.