Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen3.5 122B A10B (Non-reasoning) | Gemini 3 Flash Preview (Non-reasoning) |
|---|---|---|
| Input ($/M tokens) | $0.4 | $0.5 |
| Output ($/M tokens) | $3.2 | $3 |
Verdict. Qwen3.5 122B A10B (Non-reasoning) 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 budget bracket for output-token pricing. At 1.1× the per-million-token cost, Gemini 3 Flash Preview (Non-reasoning) is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Gemini 3 Flash Preview (Non-reasoning) makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. Qwen3.5 122B A10B (Non-reasoning) is strongest on Coding Index (43.3), Intelligence Index (28.2). Gemini 3 Flash Preview (Non-reasoning) leads on Intelligence Index (27.9).
Speed. On throughput, Gemini 3 Flash Preview (Non-reasoning) generates tokens at 195 tok/s versus 143 tok/s — about 27% faster. On time-to-first-token, Gemini 3 Flash Preview (Non-reasoning) responds in 730ms vs 2330ms, which matters most for chat-style UIs.
Provider. Alibaba and Google sell to overlapping but distinct developer audiences: Alibaba tends to ship frontier reasoning models with premium positioning, while Google 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): Qwen3.5 122B A10B (Non-reasoning) costs $60.00 ($720/year); Gemini 3 Flash Preview (Non-reasoning) costs $60.00 ($720/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Qwen3.5 122B A10B (Non-reasoning) ≈ $8.40/run, Gemini 3 Flash Preview (Non-reasoning) ≈ $8.50/run. At agent/realtime scale (200M input / 100M output per million requests): Qwen3.5 122B A10B (Non-reasoning) ≈ $400/run, Gemini 3 Flash Preview (Non-reasoning) ≈ $400/run.
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
Qwen3.5 122B A10B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.10/M tokens vs $1.13/M for Gemini 3 Flash Preview (Non-reasoning).
Qwen3.5 122B A10B (Non-reasoning) wins 2 out of 12 benchmarks compared to 0 for Gemini 3 Flash Preview (Non-reasoning). See the detailed benchmark chart above for per-category results.
Gemini 3 Flash Preview (Non-reasoning) generates tokens faster at 195 tok/s vs 143 tok/s. However, Gemini 3 Flash Preview (Non-reasoning) has lower time-to-first-token (0.73s vs 2.33s).
Choose based on your priorities: Qwen3.5 122B A10B (Non-reasoning) for lower cost, Qwen3.5 122B A10B (Non-reasoning) for stronger benchmark performance, and Gemini 3 Flash Preview (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.