Compare/Qwen3.5 35B A3B (Reasoning) vs GPT-5.1 Codex mini (high)

Qwen3.5 35B A3B (Reasoning)vsGPT-5.1 Codex mini (high)

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

Alibaba

Qwen3.5 35B A3B (Reasoning)

Input
$0.25/M
Output
$2/M
Speed
111 tok/s
TTFT
1.10s
OpenAI

GPT-5.1 Codex mini (high)

Input
$0.25/M
Output
$2/M
Speed
186 tok/s
TTFT
6.58s

Winner by Category

Cheaper
Tie
Faster (tok/s)
GPT-5.1 Codex mini (high)
Lower Latency
Qwen3.5 35B A3B (Reasoning)
Benchmarks (3-8)
GPT-5.1 Codex mini (high)

Pricing Comparison

MetricQwen3.5 35B A3B (Reasoning)GPT-5.1 Codex 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 (Reasoning)$0.45
GPT-5.1 Codex mini (high)$0.45

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen3.5 35B A3B (Reasoning)
111 tok/s
GPT-5.1 Codex mini (high)
186 tok/s
Time to First Token (seconds) — lower is better
Qwen3.5 35B A3B (Reasoning)
1.10s
GPT-5.1 Codex mini (high)
6.58s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
37.138.6
Coding Index
30.336.4
Math Index
91.7
GPQA Diamond
84.5%81.3%
MMLU-Pro
82.0%
LiveCodeBench
83.6%
AIME 2025
91.7%
MATH-500
Humanity's Last Exam
19.7%16.9%
SciCode
37.7%42.6%
IFBench
72.5%67.9%
TerminalBench
26.5%33.3%
Qwen3.5 35B A3B (Reasoning)3 wins
8 winsGPT-5.1 Codex mini (high)

Frequently Asked Questions

Which is cheaper, Qwen3.5 35B A3B (Reasoning) or GPT-5.1 Codex 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-5.1 Codex mini (high) wins 8 out of 12 benchmarks compared to 3 for Qwen3.5 35B A3B (Reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

GPT-5.1 Codex mini (high) generates tokens faster at 186 tok/s vs 111 tok/s. Qwen3.5 35B A3B (Reasoning) also has lower time-to-first-token (1.10s vs 6.58s).

When should I use Qwen3.5 35B A3B (Reasoning) vs GPT-5.1 Codex mini (high)?

Choose based on your priorities: both are similarly priced, GPT-5.1 Codex mini (high) for stronger benchmark performance, and GPT-5.1 Codex mini (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.