Compare/gpt-oss-20B (high) vs Qwen3.5 9B (Non-reasoning)

gpt-oss-20B (high)vsQwen3.5 9B (Non-reasoning)

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

OpenAI

gpt-oss-20B (high)

Input
$0.06/M
Output
$0.2/M
Speed
264 tok/s
TTFT
0.43s
Alibaba

Qwen3.5 9B (Non-reasoning)

Input
$0.04/M
Output
$0.2/M
Speed
178 tok/s
TTFT
0.54s

Winner by Category

Cheaper
Qwen3.5 9B (Non-reasoning)
Faster (tok/s)
gpt-oss-20B (high)
Lower Latency
gpt-oss-20B (high)
Benchmarks (7-4)
gpt-oss-20B (high)

Pricing Comparison

Metricgpt-oss-20B (high)Qwen3.5 9B (Non-reasoning)
Input ($/M tokens)$0.06$0.04
Output ($/M tokens)$0.2$0.2
Cost for 1M input + 100K output tokens:
gpt-oss-20B (high)$0.08
Qwen3.5 9B (Non-reasoning)$0.06

Speed Comparison

Output Speed (tokens/s) — higher is better
gpt-oss-20B (high)
264 tok/s
Qwen3.5 9B (Non-reasoning)
178 tok/s
Time to First Token (seconds) — lower is better
gpt-oss-20B (high)
0.43s
Qwen3.5 9B (Non-reasoning)
0.54s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
24.527.3
Coding Index
18.521.4
Math Index
89.3
GPQA Diamond
68.8%78.6%
MMLU-Pro
74.8%
LiveCodeBench
77.7%
AIME 2025
89.3%
MATH-500
Humanity's Last Exam
9.8%8.6%
SciCode
34.4%27.7%
IFBench
65.1%37.8%
TerminalBench
10.6%18.2%
gpt-oss-20B (high)7 wins
4 winsQwen3.5 9B (Non-reasoning)

Frequently Asked Questions

Which is cheaper, gpt-oss-20B (high) or Qwen3.5 9B (Non-reasoning)?

Qwen3.5 9B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.08/M tokens vs $0.09/M for gpt-oss-20B (high).

Which model performs better on benchmarks?

gpt-oss-20B (high) wins 7 out of 12 benchmarks compared to 4 for Qwen3.5 9B (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

gpt-oss-20B (high) generates tokens faster at 264 tok/s vs 178 tok/s. gpt-oss-20B (high) also has lower time-to-first-token (0.43s vs 0.54s).

When should I use gpt-oss-20B (high) vs Qwen3.5 9B (Non-reasoning)?

Choose based on your priorities: Qwen3.5 9B (Non-reasoning) for lower cost, gpt-oss-20B (high) for stronger benchmark performance, and gpt-oss-20B (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.