Compare/Qwen3 235B A22B (Non-reasoning) vs Apertus 70B Instruct

Qwen3 235B A22B (Non-reasoning)vsApertus 70B Instruct

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Alibaba

Qwen3 235B A22B (Non-reasoning)

Input
$0.7/M
Output
$2.8/M
Speed
46 tok/s
TTFT
1.19s
Swiss AI Initiative

Apertus 70B Instruct

Input
$0.82/M
Output
$2.92/M
Speed
64 tok/s
TTFT
1.68s

Winner by Category

Cheaper
Qwen3 235B A22B (Non-reasoning)
Faster (tok/s)
Apertus 70B Instruct
Lower Latency
Qwen3 235B A22B (Non-reasoning)
Benchmarks (11-1)
Qwen3 235B A22B (Non-reasoning)

Pricing Comparison

MetricQwen3 235B A22B (Non-reasoning)Apertus 70B Instruct
Input ($/M tokens)$0.7$0.82
Output ($/M tokens)$2.8$2.92
Cost for 1M input + 100K output tokens:
Qwen3 235B A22B (Non-reasoning)$0.98
Apertus 70B Instruct$1.11

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen3 235B A22B (Non-reasoning)
46 tok/s
Apertus 70B Instruct
64 tok/s
Time to First Token (seconds) — lower is better
Qwen3 235B A22B (Non-reasoning)
1.19s
Apertus 70B Instruct
1.68s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
17.07.7
Coding Index
14.01.9
Math Index
23.7
GPQA Diamond
61.3%27.2%
MMLU-Pro
76.2%
LiveCodeBench
34.3%
AIME 2025
23.7%
MATH-500
90.2%
Humanity's Last Exam
4.7%5.5%
SciCode
29.9%5.7%
IFBench
36.6%25.9%
TerminalBench
6.1%0.0%
Qwen3 235B A22B (Non-reasoning)11 wins
1 winsApertus 70B Instruct

Frequently Asked Questions

Which is cheaper, Qwen3 235B A22B (Non-reasoning) or Apertus 70B Instruct?

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.

Which model performs better on benchmarks?

Qwen3 235B A22B (Non-reasoning) wins 11 out of 12 benchmarks compared to 1 for Apertus 70B Instruct. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Apertus 70B Instruct generates tokens faster at 64 tok/s vs 46 tok/s. Qwen3 235B A22B (Non-reasoning) also has lower time-to-first-token (1.19s vs 1.68s).

When should I use Qwen3 235B A22B (Non-reasoning) vs Apertus 70B Instruct?

Choose based on your priorities: Qwen3 235B A22B (Non-reasoning) for lower cost, Qwen3 235B A22B (Non-reasoning) for stronger benchmark performance, and Apertus 70B Instruct for faster generation. For latency-sensitive apps, check the TTFT comparison above.