Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | DeepSeek V3.2 Exp (Reasoning) | Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) |
|---|---|---|
| Input ($/M tokens) | $0.28 | $0.1 |
| Output ($/M tokens) | $0.42 | $0.4 |
Data from Artificial Analysis API — 12 benchmarks
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.17/M tokens vs $0.32/M for DeepSeek V3.2 Exp (Reasoning).
DeepSeek V3.2 Exp (Reasoning) wins 11 out of 12 benchmarks compared to 0 for Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning). See the detailed benchmark chart above for per-category results.
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) generates tokens faster at 344 tok/s vs 32 tok/s. However, Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) has lower time-to-first-token (0.36s vs 1.48s).
Choose based on your priorities: Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) for lower cost, DeepSeek V3.2 Exp (Reasoning) for stronger benchmark performance, and Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.