Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Llama 4 Scout | Mistral Small 4 (Non-reasoning) |
|---|---|---|
| Input ($/M tokens) | $0.17 | $0.15 |
| Output ($/M tokens) | $0.66 | $0.6 |
Data from Artificial Analysis API — 12 benchmarks
Mistral Small 4 (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.26/M tokens vs $0.29/M for Llama 4 Scout.
Llama 4 Scout wins 8 out of 12 benchmarks compared to 4 for Mistral Small 4 (Non-reasoning). See the detailed benchmark chart above for per-category results.
Mistral Small 4 (Non-reasoning) generates tokens faster at 159 tok/s vs 129 tok/s. However, Mistral Small 4 (Non-reasoning) has lower time-to-first-token (0.41s vs 0.45s).
Choose based on your priorities: Mistral Small 4 (Non-reasoning) for lower cost, Llama 4 Scout for stronger benchmark performance, and Mistral Small 4 (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.