Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen3 8B (Reasoning) | GPT-5.1 Codex mini (high) |
|---|---|---|
| Input ($/M tokens) | $0.18 | $0.25 |
| Output ($/M tokens) | $2.1 | $2 |
Data from Artificial Analysis API — 12 benchmarks
Qwen3 8B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.66/M tokens vs $0.69/M for GPT-5.1 Codex mini (high).
GPT-5.1 Codex mini (high) wins 11 out of 12 benchmarks compared to 1 for Qwen3 8B (Reasoning). See the detailed benchmark chart above for per-category results.
GPT-5.1 Codex mini (high) generates tokens faster at 186 tok/s vs 90 tok/s. Qwen3 8B (Reasoning) also has lower time-to-first-token (0.92s vs 6.58s).
Choose based on your priorities: Qwen3 8B (Reasoning) for lower cost, GPT-5.1 Codex mini (high) for stronger benchmark performance, and GPT-5.1 Codex mini (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.