Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Llama 3.2 Instruct 3B | Devstral Small (May '25) |
|---|---|---|
| Input ($/M tokens) | $0.085 | $0.06 |
| Output ($/M tokens) | $0.085 | $0.12 |
Data from Artificial Analysis API — 12 benchmarks
Devstral Small (May '25) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.07/M tokens vs $0.09/M for Llama 3.2 Instruct 3B.
Devstral Small (May '25) wins 9 out of 12 benchmarks compared to 3 for Llama 3.2 Instruct 3B. See the detailed benchmark chart above for per-category results.
Llama 3.2 Instruct 3B generates tokens faster at 50 tok/s vs 0 tok/s. However, Devstral Small (May '25) has lower time-to-first-token (0.00s vs 0.35s).
Choose based on your priorities: Devstral Small (May '25) for lower cost, Devstral Small (May '25) for stronger benchmark performance, and Llama 3.2 Instruct 3B for faster generation. For latency-sensitive apps, check the TTFT comparison above.