Compare/GLM-4.7 (Non-reasoning) vs Kimi K2 0905

GLM-4.7 (Non-reasoning)vsKimi K2 0905

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

Z AI

GLM-4.7 (Non-reasoning)

Input
$0.55/M
Output
$2.15/M
Speed
77 tok/s
TTFT
0.66s
Kimi

Kimi K2 0905

Input
$0.8/M
Output
$2.25/M
Speed
63 tok/s
TTFT
0.78s

Winner by Category

Cheaper
GLM-4.7 (Non-reasoning)
Faster (tok/s)
GLM-4.7 (Non-reasoning)
Lower Latency
GLM-4.7 (Non-reasoning)
Benchmarks (5-6)
Kimi K2 0905

Pricing Comparison

MetricGLM-4.7 (Non-reasoning)Kimi K2 0905
Input ($/M tokens)$0.55$0.8
Output ($/M tokens)$2.15$2.25
Cost for 1M input + 100K output tokens:
GLM-4.7 (Non-reasoning)$0.77
Kimi K2 0905$1.03

Speed Comparison

Output Speed (tokens/s) — higher is better
GLM-4.7 (Non-reasoning)
77 tok/s
Kimi K2 0905
63 tok/s
Time to First Token (seconds) — lower is better
GLM-4.7 (Non-reasoning)
0.66s
Kimi K2 0905
0.78s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
34.230.9
Coding Index
32.025.9
Math Index
48.057.3
GPQA Diamond
66.4%76.7%
MMLU-Pro
79.4%81.9%
LiveCodeBench
56.2%61.0%
AIME 2025
48.0%57.3%
MATH-500
Humanity's Last Exam
6.1%6.3%
SciCode
35.4%30.7%
IFBench
54.6%41.7%
TerminalBench
30.3%23.5%
GLM-4.7 (Non-reasoning)5 wins
6 winsKimi K2 0905

Frequently Asked Questions

Which is cheaper, GLM-4.7 (Non-reasoning) or Kimi K2 0905?

GLM-4.7 (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.94/M tokens vs $1.14/M for Kimi K2 0905.

Which model performs better on benchmarks?

Kimi K2 0905 wins 6 out of 12 benchmarks compared to 5 for GLM-4.7 (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

GLM-4.7 (Non-reasoning) generates tokens faster at 77 tok/s vs 63 tok/s. GLM-4.7 (Non-reasoning) also has lower time-to-first-token (0.66s vs 0.78s).

When should I use GLM-4.7 (Non-reasoning) vs Kimi K2 0905?

Choose based on your priorities: GLM-4.7 (Non-reasoning) for lower cost, Kimi K2 0905 for stronger benchmark performance, and GLM-4.7 (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.