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

DeepSeek V3 (Dec '24)vsGLM-4.6V (Non-reasoning)

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

DeepSeek

DeepSeek V3 (Dec '24)

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

GLM-4.6V (Non-reasoning)

Input
$0.3/M
Output
$0.9/M
Speed
21 tok/s
TTFT
1.51s

Winner by Category

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

Pricing Comparison

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

Speed Comparison

Output Speed (tokens/s) — higher is better
DeepSeek V3 (Dec '24)
GLM-4.6V (Non-reasoning)
21 tok/s
Time to First Token (seconds) — lower is better
DeepSeek V3 (Dec '24)
GLM-4.6V (Non-reasoning)
1.51s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
16.517.1
Coding Index
16.411.1
Math Index
26.026.3
GPQA Diamond
55.7%56.6%
MMLU-Pro
75.2%75.2%
LiveCodeBench
35.9%41.1%
AIME 2025
26.0%26.3%
MATH-500
88.7%
Humanity's Last Exam
3.6%3.7%
SciCode
35.4%27.2%
IFBench
34.8%27.9%
TerminalBench
6.8%3.0%
DeepSeek V3 (Dec '24)5 wins
6 winsGLM-4.6V (Non-reasoning)

Frequently Asked Questions

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

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 21 tok/s vs 0 tok/s. DeepSeek V3 (Dec '24) also has lower time-to-first-token (0.00s vs 1.51s).

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

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.