Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen3 235B A22B (Non-reasoning) | Apertus 70B Instruct |
|---|---|---|
| Input ($/M tokens) | $0.7 | $0.82 |
| Output ($/M tokens) | $2.8 | $2.92 |
Verdict. Qwen3 235B A22B (Non-reasoning) wins the overall benchmark matchup 1–0 across 1 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 1.0× the per-million-token cost, Qwen3 235B A22B (Non-reasoning) is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Qwen3 235B A22B (Non-reasoning) makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. Qwen3 235B A22B (Non-reasoning) is strongest on Intelligence Index (10.8). Apertus 70B Instruct leads on Intelligence Index (2.0).
Speed. Speed data is incomplete for this pair; benchmark and price should decide.
Provider. Alibaba and Swiss AI Initiative sell to overlapping but distinct developer audiences: Alibaba tends to ship frontier reasoning models with premium positioning, while Swiss AI Initiative 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 235B A22B (Non-reasoning) costs $63.00 ($756/year); Apertus 70B Instruct costs $68.40 ($821/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Qwen3 235B A22B (Non-reasoning) ≈ $9.10/run, Apertus 70B Instruct ≈ $9.94/run. At agent/realtime scale (200M input / 100M output per million requests): Qwen3 235B A22B (Non-reasoning) ≈ $420/run, Apertus 70B Instruct ≈ $456/run. Qwen3 235B A22B (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 235B A22B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.23/M tokens vs $1.34/M for Apertus 70B Instruct.
Qwen3 235B A22B (Non-reasoning) wins 1 out of 12 benchmarks compared to 0 for Apertus 70B Instruct. See the detailed benchmark chart above for per-category results.
Qwen3 235B A22B (Non-reasoning) generates tokens faster at 59 tok/s vs — tok/s. Qwen3 235B A22B (Non-reasoning) also has lower time-to-first-token (2.65s vs —s).
Choose based on your priorities: Qwen3 235B A22B (Non-reasoning) for lower cost, Qwen3 235B A22B (Non-reasoning) for stronger benchmark performance, and Qwen3 235B A22B (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.