Compare/Qwen3.5 397B A17B (Reasoning) vs GLM-5 (Non-reasoning)

Qwen3.5 397B A17B (Reasoning)vsGLM-5 (Non-reasoning)

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

Alibaba

Qwen3.5 397B A17B (Reasoning)

Input
$0.6/M
Output
$3.6/M
Speed
54 tok/s
TTFT
1.39s
Z AI

GLM-5 (Non-reasoning)

Input
$1/M
Output
$3.2/M
Speed
61 tok/s
TTFT
1.08s

Winner by Category

Cheaper
Qwen3.5 397B A17B (Reasoning)
Faster (tok/s)
GLM-5 (Non-reasoning)
Lower Latency
GLM-5 (Non-reasoning)
Benchmarks (7-0)
Qwen3.5 397B A17B (Reasoning)

Pricing Comparison

MetricQwen3.5 397B A17B (Reasoning)GLM-5 (Non-reasoning)
Input ($/M tokens)$0.6$1
Output ($/M tokens)$3.6$3.2
Cost for 1M input + 100K output tokens:
Qwen3.5 397B A17B (Reasoning)$0.96
GLM-5 (Non-reasoning)$1.32

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen3.5 397B A17B (Reasoning)
54 tok/s
GLM-5 (Non-reasoning)
61 tok/s
Time to First Token (seconds) — lower is better
Qwen3.5 397B A17B (Reasoning)
1.39s
GLM-5 (Non-reasoning)
1.08s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
45.040.6
Coding Index
41.339.0
Math Index
GPQA Diamond
89.3%66.6%
MMLU-Pro
LiveCodeBench
AIME 2025
MATH-500
Humanity's Last Exam
27.3%7.2%
SciCode
42.0%38.3%
IFBench
78.8%55.2%
TerminalBench
40.9%39.4%
Qwen3.5 397B A17B (Reasoning)7 wins
0 winsGLM-5 (Non-reasoning)

Frequently Asked Questions

Which is cheaper, Qwen3.5 397B A17B (Reasoning) or GLM-5 (Non-reasoning)?

Qwen3.5 397B A17B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.35/M tokens vs $1.55/M for GLM-5 (Non-reasoning).

Which model performs better on benchmarks?

Qwen3.5 397B A17B (Reasoning) wins 7 out of 12 benchmarks compared to 0 for GLM-5 (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

GLM-5 (Non-reasoning) generates tokens faster at 61 tok/s vs 54 tok/s. However, GLM-5 (Non-reasoning) has lower time-to-first-token (1.08s vs 1.39s).

When should I use Qwen3.5 397B A17B (Reasoning) vs GLM-5 (Non-reasoning)?

Choose based on your priorities: Qwen3.5 397B A17B (Reasoning) for lower cost, Qwen3.5 397B A17B (Reasoning) for stronger benchmark performance, and GLM-5 (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.