Compare/Qwen3.6 35B A3B (Reasoning) vs GLM-4.7 (Non-reasoning)

Qwen3.6 35B A3B (Reasoning)vsGLM-4.7 (Non-reasoning)

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

Alibaba

Qwen3.6 35B A3B (Reasoning)

Input
$0.375/M
Output
$2.25/M
Speed
238 tok/s
TTFT
1.79s
Z AI

GLM-4.7 (Non-reasoning)

Input
$0.6/M
Output
$2.2/M
Speed
87 tok/s
TTFT
0.69s

Winner by Category

Cheaper
Qwen3.6 35B A3B (Reasoning)
Faster (tok/s)
Qwen3.6 35B A3B (Reasoning)
Lower Latency
GLM-4.7 (Non-reasoning)
Benchmarks (7-4)
Qwen3.6 35B A3B (Reasoning)

Pricing Comparison

MetricQwen3.6 35B A3B (Reasoning)GLM-4.7 (Non-reasoning)
Input ($/M tokens)$0.375$0.6
Output ($/M tokens)$2.25$2.2
Cost for 1M input + 100K output tokens:
Qwen3.6 35B A3B (Reasoning)$0.60
GLM-4.7 (Non-reasoning)$0.82

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen3.6 35B A3B (Reasoning)
238 tok/s
GLM-4.7 (Non-reasoning)
87 tok/s
Time to First Token (seconds) — lower is better
Qwen3.6 35B A3B (Reasoning)
1.79s
GLM-4.7 (Non-reasoning)
0.69s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
43.534.2
Coding Index
35.132.0
Math Index
48.0
GPQA Diamond
84.1%66.4%
MMLU-Pro
79.4%
LiveCodeBench
56.2%
AIME 2025
48.0%
MATH-500
Humanity's Last Exam
20.2%6.1%
SciCode
35.8%35.4%
IFBench
64.4%54.6%
TerminalBench
34.8%30.3%
Qwen3.6 35B A3B (Reasoning)7 wins
4 winsGLM-4.7 (Non-reasoning)

Frequently Asked Questions

Which is cheaper, Qwen3.6 35B A3B (Reasoning) or GLM-4.7 (Non-reasoning)?

Qwen3.6 35B A3B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.84/M tokens vs $1.00/M for GLM-4.7 (Non-reasoning).

Which model performs better on benchmarks?

Qwen3.6 35B A3B (Reasoning) wins 7 out of 12 benchmarks compared to 4 for GLM-4.7 (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Qwen3.6 35B A3B (Reasoning) generates tokens faster at 238 tok/s vs 87 tok/s. However, GLM-4.7 (Non-reasoning) has lower time-to-first-token (0.69s vs 1.79s).

When should I use Qwen3.6 35B A3B (Reasoning) vs GLM-4.7 (Non-reasoning)?

Choose based on your priorities: Qwen3.6 35B A3B (Reasoning) for lower cost, Qwen3.6 35B A3B (Reasoning) for stronger benchmark performance, and Qwen3.6 35B A3B (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.