Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | MiniMax M1 80k | Qwen3.6 35B A3B (Non-reasoning) |
|---|---|---|
| Input ($/M tokens) | $0.55 | $0.38 |
| Output ($/M tokens) | $2.2 | $2.25 |
Verdict. Qwen3.6 35B A3B (Non-reasoning) takes the aggregate benchmark matchup 2–0 across 2 categories. Real workloads usually care about a handful of specific tasks — see the per-benchmark table above.
Pricing. Both models sit in the budget bracket for output-token pricing. At 1.0× the per-million-token cost, MiniMax M1 80k is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). MiniMax M1 80k makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. MiniMax M1 80k is strongest on Intelligence Index (17.9). Qwen3.6 35B A3B (Non-reasoning) leads on Coding Index (28.1), Intelligence Index (24.6).
Speed. Speed data is incomplete for this pair; benchmark and price should decide.
Provider. MiniMax and Alibaba sell to overlapping but distinct developer audiences: MiniMax tends to ship frontier reasoning models with premium positioning, while Alibaba 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): MiniMax M1 80k costs $49.50 ($594/year); Qwen3.6 35B A3B (Non-reasoning) costs $45.15 ($542/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): MiniMax M1 80k ≈ $7.15/run, Qwen3.6 35B A3B (Non-reasoning) ≈ $6.40/run. At agent/realtime scale (200M input / 100M output per million requests): MiniMax M1 80k ≈ $330/run, Qwen3.6 35B A3B (Non-reasoning) ≈ $301/run. Qwen3.6 35B A3B (Non-reasoning) 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
Qwen3.6 35B A3B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.85/M tokens vs $0.96/M for MiniMax M1 80k.
Qwen3.6 35B A3B (Non-reasoning) wins 2 out of 12 benchmarks compared to 0 for MiniMax M1 80k. See the detailed benchmark chart above for per-category results.
Qwen3.6 35B A3B (Non-reasoning) generates tokens faster at 137 tok/s vs — tok/s. However, Qwen3.6 35B A3B (Non-reasoning) has lower time-to-first-token (2.05s vs —s).
Choose based on your priorities: Qwen3.6 35B A3B (Non-reasoning) for lower cost, Qwen3.6 35B A3B (Non-reasoning) for stronger benchmark performance, and Qwen3.6 35B A3B (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.