Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Gemini 3 Pro Preview (high) | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) |
|---|---|---|
| Input ($/M tokens) | $2 | $2 |
| Output ($/M tokens) | $12 | $10 |
Data from Artificial Analysis API — 12 benchmarks
Claude Sonnet 5 (Adaptive Reasoning, Max Effort) is cheaper overall. Its blended price (3:1 input/output ratio) is $4.00/M tokens vs $4.50/M for Gemini 3 Pro Preview (high).
Gemini 3 Pro Preview (high) wins 7 out of 12 benchmarks compared to 4 for Claude Sonnet 5 (Adaptive Reasoning, Max Effort). See the detailed benchmark chart above for per-category results.
Claude Sonnet 5 (Adaptive Reasoning, Max Effort) generates tokens faster at 87 tok/s vs 0 tok/s. Gemini 3 Pro Preview (high) also has lower time-to-first-token (0.00s vs 134.45s).
Choose based on your priorities: Claude Sonnet 5 (Adaptive Reasoning, Max Effort) for lower cost, Gemini 3 Pro Preview (high) for stronger benchmark performance, and Claude Sonnet 5 (Adaptive Reasoning, Max Effort) for faster generation. For latency-sensitive apps, check the TTFT comparison above.