Compare/GLM-4.6V (Non-reasoning) vs DeepSeek V3 (Dec '24)

GLM-4.6V (Non-reasoning)vsDeepSeek V3 (Dec '24)

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

Z AI

GLM-4.6V (Non-reasoning)

Input
$0.3/M
Output
$0.9/M
Speed
23 tok/s
TTFT
5.88s
DeepSeek

DeepSeek V3 (Dec '24)

Input
$0.4/M
Output
$0.89/M
Speed
TTFT

Winner by Category

Cheaper
GLM-4.6V (Non-reasoning)
Faster (tok/s)
GLM-4.6V (Non-reasoning)
Lower Latency
DeepSeek V3 (Dec '24)
Benchmarks (6-5)
GLM-4.6V (Non-reasoning)

Pricing Comparison

MetricGLM-4.6V (Non-reasoning)DeepSeek V3 (Dec '24)
Input ($/M tokens)$0.3$0.4
Output ($/M tokens)$0.9$0.89
Cost for 1M input + 100K output tokens:
GLM-4.6V (Non-reasoning)$0.39
DeepSeek V3 (Dec '24)$0.49

Speed Comparison

Output Speed (tokens/s) — higher is better
GLM-4.6V (Non-reasoning)
23 tok/s
DeepSeek V3 (Dec '24)
Time to First Token (seconds) — lower is better
GLM-4.6V (Non-reasoning)
5.88s
DeepSeek V3 (Dec '24)

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
17.116.5
Coding Index
11.116.4
Math Index
26.326.0
GPQA Diamond
56.6%55.7%
MMLU-Pro
75.2%75.2%
LiveCodeBench
41.1%35.9%
AIME 2025
26.3%26.0%
MATH-500
88.7%
Humanity's Last Exam
3.7%3.6%
SciCode
27.2%35.4%
IFBench
27.9%34.8%
TerminalBench
3.0%6.8%
GLM-4.6V (Non-reasoning)6 wins
5 winsDeepSeek V3 (Dec '24)

Frequently Asked Questions

Which is cheaper, GLM-4.6V (Non-reasoning) or DeepSeek V3 (Dec '24)?

GLM-4.6V (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.45/M tokens vs $0.63/M for DeepSeek V3 (Dec '24).

Which model performs better on benchmarks?

GLM-4.6V (Non-reasoning) wins 6 out of 12 benchmarks compared to 5 for DeepSeek V3 (Dec '24). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

GLM-4.6V (Non-reasoning) generates tokens faster at 23 tok/s vs 0 tok/s. However, DeepSeek V3 (Dec '24) has lower time-to-first-token (0.00s vs 5.88s).

When should I use GLM-4.6V (Non-reasoning) vs DeepSeek V3 (Dec '24)?

Choose based on your priorities: GLM-4.6V (Non-reasoning) for lower cost, GLM-4.6V (Non-reasoning) for stronger benchmark performance, and GLM-4.6V (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.