Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | GPT-5.1 Codex (high) | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) |
|---|---|---|
| Input ($/M tokens) | $1.25 | $2 |
| Output ($/M tokens) | $10 | $10 |
Data from Artificial Analysis API — 12 benchmarks
GPT-5.1 Codex (high) is cheaper overall. Its blended price (3:1 input/output ratio) is $3.44/M tokens vs $4.00/M for Claude Sonnet 5 (Adaptive Reasoning, Max Effort).
GPT-5.1 Codex (high) wins 6 out of 12 benchmarks compared to 5 for Claude Sonnet 5 (Adaptive Reasoning, Max Effort). See the detailed benchmark chart above for per-category results.
GPT-5.1 Codex (high) generates tokens faster at 189 tok/s vs 87 tok/s. GPT-5.1 Codex (high) also has lower time-to-first-token (4.13s vs 134.45s).
Choose based on your priorities: GPT-5.1 Codex (high) for lower cost, GPT-5.1 Codex (high) for stronger benchmark performance, and GPT-5.1 Codex (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.