Compare/GLM-5 (Reasoning) vs Qwen3.5 122B A10B (Non-reasoning)

GLM-5 (Reasoning)vsQwen3.5 122B A10B (Non-reasoning)

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

Z AI

GLM-5 (Reasoning)

Input
$1/M
Output
$3.2/M
Speed
60 tok/s
TTFT
0.96s
Alibaba

Qwen3.5 122B A10B (Non-reasoning)

Input
$0.4/M
Output
$3.2/M
Speed
149 tok/s
TTFT
1.00s

Winner by Category

Cheaper
Qwen3.5 122B A10B (Non-reasoning)
Faster (tok/s)
Qwen3.5 122B A10B (Non-reasoning)
Lower Latency
GLM-5 (Reasoning)
Benchmarks (6-1)
GLM-5 (Reasoning)

Pricing Comparison

MetricGLM-5 (Reasoning)Qwen3.5 122B A10B (Non-reasoning)
Input ($/M tokens)$1$0.4
Output ($/M tokens)$3.2$3.2
Cost for 1M input + 100K output tokens:
GLM-5 (Reasoning)$1.32
Qwen3.5 122B A10B (Non-reasoning)$0.72

Speed Comparison

Output Speed (tokens/s) — higher is better
GLM-5 (Reasoning)
60 tok/s
Qwen3.5 122B A10B (Non-reasoning)
149 tok/s
Time to First Token (seconds) — lower is better
GLM-5 (Reasoning)
0.96s
Qwen3.5 122B A10B (Non-reasoning)
1.00s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
49.835.9
Coding Index
44.231.6
Math Index
GPQA Diamond
82.0%82.7%
MMLU-Pro
LiveCodeBench
AIME 2025
MATH-500
Humanity's Last Exam
27.2%14.8%
SciCode
46.2%35.6%
IFBench
72.3%50.8%
TerminalBench
43.2%29.5%
GLM-5 (Reasoning)6 wins
1 winsQwen3.5 122B A10B (Non-reasoning)

Frequently Asked Questions

Which is cheaper, GLM-5 (Reasoning) or Qwen3.5 122B A10B (Non-reasoning)?

Qwen3.5 122B A10B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.10/M tokens vs $1.55/M for GLM-5 (Reasoning).

Which model performs better on benchmarks?

GLM-5 (Reasoning) wins 6 out of 12 benchmarks compared to 1 for Qwen3.5 122B A10B (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Qwen3.5 122B A10B (Non-reasoning) generates tokens faster at 149 tok/s vs 60 tok/s. GLM-5 (Reasoning) also has lower time-to-first-token (0.96s vs 1.00s).

When should I use GLM-5 (Reasoning) vs Qwen3.5 122B A10B (Non-reasoning)?

Choose based on your priorities: Qwen3.5 122B A10B (Non-reasoning) for lower cost, GLM-5 (Reasoning) for stronger benchmark performance, and Qwen3.5 122B A10B (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.