Compare/Qwen3.5 35B A3B (Non-reasoning) vs GPT-5 mini (high)

Qwen3.5 35B A3B (Non-reasoning)vsGPT-5 mini (high)

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

Alibaba

Qwen3.5 35B A3B (Non-reasoning)

Input
$0.25/M
Output
$2/M
Speed
119 tok/s
TTFT
0.98s
OpenAI

GPT-5 mini (high)

Input
$0.25/M
Output
$2/M
Speed
88 tok/s
TTFT
86.49s

Winner by Category

Cheaper
Tie
Faster (tok/s)
Qwen3.5 35B A3B (Non-reasoning)
Lower Latency
Qwen3.5 35B A3B (Non-reasoning)
Benchmarks (0-11)
GPT-5 mini (high)

Pricing Comparison

MetricQwen3.5 35B A3B (Non-reasoning)GPT-5 mini (high)
Input ($/M tokens)$0.25$0.25
Output ($/M tokens)$2$2
Cost for 1M input + 100K output tokens:
Qwen3.5 35B A3B (Non-reasoning)$0.45
GPT-5 mini (high)$0.45

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen3.5 35B A3B (Non-reasoning)
119 tok/s
GPT-5 mini (high)
88 tok/s
Time to First Token (seconds) — lower is better
Qwen3.5 35B A3B (Non-reasoning)
0.98s
GPT-5 mini (high)
86.49s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
30.741.2
Coding Index
16.835.3
Math Index
90.7
GPQA Diamond
81.9%82.8%
MMLU-Pro
83.7%
LiveCodeBench
83.8%
AIME 2025
90.7%
MATH-500
Humanity's Last Exam
12.8%19.7%
SciCode
29.3%39.2%
IFBench
44.5%75.4%
TerminalBench
10.6%33.3%
Qwen3.5 35B A3B (Non-reasoning)0 wins
11 winsGPT-5 mini (high)

Frequently Asked Questions

Which is cheaper, Qwen3.5 35B A3B (Non-reasoning) or GPT-5 mini (high)?

Both models have similar pricing. Check the detailed breakdown above for input vs output token costs.

Which model performs better on benchmarks?

GPT-5 mini (high) wins 11 out of 12 benchmarks compared to 0 for Qwen3.5 35B A3B (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Qwen3.5 35B A3B (Non-reasoning) generates tokens faster at 119 tok/s vs 88 tok/s. Qwen3.5 35B A3B (Non-reasoning) also has lower time-to-first-token (0.98s vs 86.49s).

When should I use Qwen3.5 35B A3B (Non-reasoning) vs GPT-5 mini (high)?

Choose based on your priorities: both are similarly priced, GPT-5 mini (high) for stronger benchmark performance, and Qwen3.5 35B A3B (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.