Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Llama 3.2 Instruct 90B (Vision) | Gemini 3.1 Flash-Lite Preview |
|---|---|---|
| Input ($/M tokens) | $1.38 | $0.25 |
| Output ($/M tokens) | $1.38 | $1.5 |
Data from Artificial Analysis API — 12 benchmarks
Gemini 3.1 Flash-Lite Preview is cheaper overall. Its blended price (3:1 input/output ratio) is $0.56/M tokens vs $1.38/M for Llama 3.2 Instruct 90B (Vision).
Gemini 3.1 Flash-Lite Preview wins 7 out of 12 benchmarks compared to 3 for Llama 3.2 Instruct 90B (Vision). See the detailed benchmark chart above for per-category results.
Gemini 3.1 Flash-Lite Preview generates tokens faster at 284 tok/s vs 45 tok/s. Llama 3.2 Instruct 90B (Vision) also has lower time-to-first-token (0.57s vs 5.00s).
Choose based on your priorities: Gemini 3.1 Flash-Lite Preview for lower cost, Gemini 3.1 Flash-Lite Preview for stronger benchmark performance, and Gemini 3.1 Flash-Lite Preview for faster generation. For latency-sensitive apps, check the TTFT comparison above.