Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Gemini 3.5 Flash (high) | Nova 2.0 Pro Preview (medium) |
|---|---|---|
| Input ($/M tokens) | $1.5 | $1.25 |
| Output ($/M tokens) | $9 | $10 |
Verdict. Gemini 3.5 Flash (high) wins the overall benchmark matchup 2–0 across 2 overlapping categories, but raw benchmark score is only one input to the decision.
Pricing. Both models sit in the mid-tier bracket for output-token pricing. At 0.9× the per-million-token cost, Gemini 3.5 Flash (high) is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Gemini 3.5 Flash (high) makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. Gemini 3.5 Flash (high) is strongest on Coding Index (70.1), Intelligence Index (52.0). Nova 2.0 Pro Preview (medium) leads on Coding Index (34.0), Intelligence Index (22.1).
Speed. On throughput, Gemini 3.5 Flash (high) generates tokens at 171 tok/s versus 115 tok/s — about 32% faster. On time-to-first-token, Nova 2.0 Pro Preview (medium) responds in 13020ms vs 27290ms, which matters most for chat-style UIs.
Provider. Google and Amazon sell to overlapping but distinct developer audiences: Google tends to ship frontier reasoning models with premium positioning, while Amazon often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.
Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): Gemini 3.5 Flash (high) costs $180.00 ($2160/year); Nova 2.0 Pro Preview (medium) costs $187.50 ($2250/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Gemini 3.5 Flash (high) ≈ $25.50/run, Nova 2.0 Pro Preview (medium) ≈ $26.25/run. At agent/realtime scale (200M input / 100M output per million requests): Gemini 3.5 Flash (high) ≈ $1200/run, Nova 2.0 Pro Preview (medium) ≈ $1250/run. Gemini 3.5 Flash (high) becomes more attractive at higher volume — the absolute per-token pricing difference compounds when you ship at scale.
Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.
Data from Artificial Analysis API — 12 benchmarks
Gemini 3.5 Flash (high) is cheaper overall. Its blended price (3:1 input/output ratio) is $3.38/M tokens vs $3.44/M for Nova 2.0 Pro Preview (medium).
Gemini 3.5 Flash (high) wins 2 out of 12 benchmarks compared to 0 for Nova 2.0 Pro Preview (medium). See the detailed benchmark chart above for per-category results.
Gemini 3.5 Flash (high) generates tokens faster at 171 tok/s vs 115 tok/s. However, Nova 2.0 Pro Preview (medium) has lower time-to-first-token (13.02s vs 27.29s).
Choose based on your priorities: Gemini 3.5 Flash (high) for lower cost, Gemini 3.5 Flash (high) for stronger benchmark performance, and Gemini 3.5 Flash (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.